CN111949986A

CN111949986A - Service processing method, system and storage medium

Info

Publication number: CN111949986A
Application number: CN202010103073.9A
Authority: CN
Inventors: 杜宁; 王蜀洪; 王天雨
Original assignee: Huakong Tsingjiao Information Technology Beijing Co Ltd
Current assignee: Huakong Tsingjiao Information Technology Beijing Co Ltd
Priority date: 2020-02-19
Filing date: 2020-02-19
Publication date: 2020-11-17
Anticipated expiration: 2040-02-19
Also published as: CN111949986B

Abstract

The application discloses a service processing method, a service processing system and a storage medium. The service processing method is applicable to a service processing system at least comprising terminal equipment, wherein the terminal equipment is used for providing an untrusted execution environment and a trusted execution environment, an artificial intelligence model is installed in the untrusted execution environment, and the service processing method comprises the following steps: during the operation of a service processing task by the terminal equipment, operating an artificial intelligence model in an untrusted execution environment to obtain data to be processed; executing a service processing task by using the data to be processed under the condition of confirming that the credibility verification result of the artificial intelligence model is credible; the trustworthiness verification result comes from the trusted execution environment. The method and the device confirm the artificial intelligence model running in the untrusted execution environment and the running result thereof are honest and not tampered by confirming the credibility verification result stored in the trusted execution environment.

Description

Service processing method, system and storage medium

Technical Field

The present application relates to the field of computers, and in particular, to a service processing method, a service processing system, a terminal device, a server device, a service processing software system, and a computer-readable storage medium based on an artificial intelligence model.

Background

As the hardware of the terminal device is upgraded, more and more terminal devices are able to handle artificial intelligence models, such as trained neural network models and the like. Some artificial intelligence models input data related to security level, such as PIN codes, fingerprint features, etc., so that the terminal device needs to have higher capability of protecting the security level data.

However, terminal devices are of a wide variety and vary in security; furthermore, the data of security level is not necessarily or stably stored in the terminal device, such as human face features, fingerprint features, voiceprint features, and the like. This entails that the trustworthiness of the program itself that processes the security level data installed in the terminal device needs to be guaranteed.

Disclosure of Invention

In view of the above-mentioned shortcomings of the related art, the present application aims to provide a business processing method, an artificial intelligence model-based business processing system, a terminal device, a server device, a business processing software system, and a computer-readable storage medium.

To achieve the above and other related objects, in a first aspect, the present application discloses a service processing method, which is applied in a service processing system at least including a terminal device, where an artificial intelligence model operating in an untrusted execution environment is configured, the service processing method including: the artificial intelligence model is operated during the operation of the service processing task of the terminal equipment to obtain data to be processed; under the condition that the credibility verification result of the artificial intelligence model is confirmed to be credible, the data to be processed is utilized to execute the business processing task; the trust verification result is from a trusted execution environment.

A second aspect of the present application provides a service processing method, which is applied to a service processing system configured by a terminal device and a server device, and includes: obtaining a credibility verification result; the credibility verification result is obtained by verifying the credibility of the artificial intelligence model operated in the untrusted execution environment in the terminal equipment; during the operation of the business processing task, under the condition that the credibility verification result is confirmed to be credible, cooperatively processing the data to be processed in the terminal equipment with the terminal equipment so as to execute the corresponding business processing task; wherein the data to be processed is obtained by running the artificial intelligence model in the untrusted execution environment.

A third aspect of the present application provides a service processing system based on an artificial intelligence model, including: a terminal device, at least providing an untrusted execution environment and a trusted execution environment, configured to execute the service processing method according to the first aspect; and the server side equipment is communicated with the terminal equipment and is used for sending at least one pre-generated verification execution program to the terminal equipment so as to obtain a credibility verification result after the execution of a credible execution environment in the terminal equipment.

In some embodiments of the third aspect, the server device performs the service processing method as claimed in the second aspect based on the triggering operation of the terminal device.

A fourth aspect of the present application provides a terminal device, including: the storage device is used for storing a program for describing the artificial intelligence model, at least one business processing program and a credibility verification result; a processing device in communication with the memory device over a bus, comprising: a first processing unit, configured in an untrusted execution environment, for invoking and executing the at least one business processing program, and running the artificial intelligence model in the untrusted execution environment, to execute the business processing method according to any one of the first aspect; the second processing unit is configured in a trusted execution environment and used for reading the credibility verification result; wherein data is communicated between the trusted execution environment and the untrusted execution environment.

A fifth aspect of the present application provides a terminal device, including: the storage device is used for storing a program for describing the artificial intelligence model, at least one business processing program and a credibility verification result; processing means, in communication with said storage means via a bus, configured in an untrusted execution environment, for invoking and executing said at least one business process, and running said artificial intelligence model in said untrusted execution environment, for performing the business process method according to the first aspect; the interface device is used for being in communication connection with a verification device to obtain a credibility verification result; wherein the verification device provides a trusted execution environment and stores the trustworthiness verification result.

A sixth aspect of the present application provides a server device, including: the interface device is used for receiving data to be processed and a credibility verification result from the terminal equipment; storage means for storing at least one program; processing means for calling said at least one program to coordinate said interface means and storage means to execute the service processing method as described in the second aspect.

A seventh aspect of the present application provides a computer-readable storage medium, characterized by storing at least one program, which when called executes and implements the service processing method according to any one of the first aspects, or executes and implements the service processing method according to any one of the second aspects.

An eighth aspect of the present application provides a service processing software system, configured in a service processing system at least including a terminal device, where the terminal device is configured to provide an untrusted execution environment and a trusted execution environment, where an artificial intelligence model is installed in the untrusted execution environment, and the service processing software system includes: the service operation module is used for operating the artificial intelligence model in the untrusted execution environment during the operation of the service processing task so as to obtain data to be processed; and the data processing system is used for executing the service processing task by using the data to be processed under the condition that the credibility verification result is confirmed to be credible; the credibility verification result is obtained by performing credibility verification on an artificial intelligence model running in the untrusted execution environment, and the credibility verification result is obtained from the credible execution environment.

A ninth aspect of the present application provides a service processing software system configured in a service processing system constructed by a terminal device and a server device, wherein the service processing software system includes: the service operation module is used for acquiring a credibility verification result from the terminal equipment; the credibility verification result is obtained by verifying the credibility of the artificial intelligence model operated in the untrusted execution environment in the terminal equipment; and the data processing system is used for processing the data to be processed in the terminal equipment in a coordinated manner with the terminal equipment to execute the corresponding business processing task in a state that the credibility verification result is confirmed to be credible during the running of the business processing task; wherein the data to be processed is obtained by running the artificial intelligence model in the untrusted execution environment.

In summary, the service processing method, the service processing system based on the artificial intelligence model, the terminal device, the server device, the service processing software system, and the computer readable storage medium provided by the present application confirm the credibility verification result stored in the trusted execution environment to determine that the artificial intelligence model running in the untrusted execution environment and the running result thereof are honest and not tampered, so as to ensure that the running result provided by the artificial intelligence model used by the service processing task is security level data. It is especially suitable for the fields of security, finance, insurance, investment, etc.

Drawings

The specific features of the invention to which this application relates are set forth in the appended claims. The features and advantages of the invention to which this application relates will be better understood by reference to the exemplary embodiments described in detail below and the accompanying drawings. The brief description of the drawings is as follows:

fig. 1 is a schematic structural diagram of a terminal device according to the present application in some examples.

Fig. 2 is a schematic flow chart illustrating the operation security verification performed in the verification method of the present application.

Fig. 3 is a schematic flow chart illustrating the operability verification performed in the verification method of the present application.

Fig. 4 is a schematic flow chart illustrating the integrity verification performed in the verification method of the present application.

Fig. 5 is a flowchart illustrating that the business processing system of the present application performs business processing using the result of the plausibility verification.

Fig. 6 is a flowchart illustrating a business processing task executed by the business processing system of the present application.

Fig. 7 is a diagram showing an architecture of the software trust verification system of the present application.

Fig. 8 is a schematic diagram of a network architecture provided for the present application based on the authentication scheme and the service processing scheme described in the present application.

Fig. 9 is a schematic structural diagram of an embodiment of a trusted authentication device according to the present application.

Fig. 10 is a schematic diagram illustrating an architecture of a second software trust verification system according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application is provided for illustrative purposes, and other advantages and capabilities of the present application will become apparent to those skilled in the art from the present disclosure.

Although the terms first, second, etc. may be used herein to describe various elements or parameters in some instances, these elements or parameters should not be limited by these terms. These terms are only used to distinguish one parameter from another. For example, a first operational result may be referred to as a second operational result, and similarly, a second operational result may be referred to as a first operational result, without departing from the scope of the various described embodiments. Both the first operational result and the second operational result are described as one operational result, but they are not the same operational result unless the context clearly dictates otherwise.

Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used in this specification, specify the presence of stated features, steps, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, steps, operations, elements, components, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions, steps or operations are inherently mutually exclusive in some way.

A terminal device generally refers to a device that inputs information such as a program and/or data to a remote computer via a communication facility, or receives information such as a processing result from the remote computer. The terminal devices are typically located at convenient locations where they can be operatively coupled to a remote computer using a communications facility, with numerous discrete terminal devices being communicatively coupled to the remote computer via the communications facility.

The terminal equipment not only has the functions of inputting information and outputting information, but also is suitable for a workplace so as to provide calculation processing operation matched with the workplace. Here, the calculation processing operation performed by the terminal device is generally performed by a service processing program (also referred to as Application, APP) stored in the terminal device in advance. When the service processing program is called, the terminal device can perform calculation processing on locally acquired information or information input by a remote computer to provide a corresponding service processing task.

The service processing program is usually executed by the terminal device alone or by the terminal device and the remote computer in cooperation, and provides a program with richer use experience for the user holding the terminal device in order to improve the deficiency and personalization of the original system of the terminal device. Examples of the service processing program include: and providing the program of the internet service for the user and providing the program of the local operation for the user. The pre-stored service processing program can come from an application Store (APP Store) or a program implanted before leaving a factory according to the working place of the terminal device. Taking a terminal device as an example, the service processing program includes: social applications, e-commerce shopping applications, hotel travel applications, search applications, and the like. Taking a terminal device as an example of a security monitoring terminal device, the service processing program comprises: living body recognition type programs, attitude tracking/recognition type programs, traffic monitoring type programs, and the like. Taking a terminal device as an example of a payment terminal device, the service processing program includes: self-service payment program, transfer transaction program, commodity identification program, etc. Taking terminal equipment as an access control terminal equipment as an example, the service processing program comprises: providing access service type programs according to the recognized user authority, according to the user posture, and the like.

In the above-exemplified terminal devices, for convenience of carrying and installation, the terminal devices are mostly in data communication with remote computers located in the internet through a mobile network. For this purpose, a SIM card for accessing the mobile network is usually provided in the terminal device, and a secure storage unit for storing a PIN code is provided in the SIM card, so that the terminal device provides some secure memory for storing data of a security level in hardware. However, as the power of the terminal device increases, data of a security level such as a PIN code needs to be read out from a secure memory at the time of operation, which makes it possible that the PIN code is in an untrusted execution environment. Alternatively, the data of the other security levels is not from the secure memory, but from the acquisition hardware of the terminal device, from a remote computer, or from other terminal devices, etc. To maintain privacy and data security, in some examples, the terminal device stores and executes programs that process data at a security level by a trusted execution environment that is separately configured by the terminal device. Under the condition that hardware configurations of terminal devices on the market are different, trusted execution environments configured in the terminal devices on the market are also not uniform, so that the data processing capabilities of the trusted execution environments are different, and therefore, programs with high requirements on computing capabilities are usually operated in untrusted execution environments. Examples of such programs include programs designed using artificial intelligence models, or the aforementioned business process programs, and the like. The artificial intelligence model refers to a data processing logic designed by using a machine-learnable algorithm, and is used for performing recognition, classification, verification, and the like related to business processing on input data. The artificial intelligence model describes the corresponding processing logic through a program and runs in an untrusted execution environment. Wherein a program describing an artificial intelligence model is said to run when the program is invoked for execution. Wherein the machine-learnable algorithms include, but are not limited to: neural network algorithms, decision tree algorithms, clustering algorithms, random forest algorithms, genetic algorithms, and the like. The artificial intelligence model functionally includes, but is not limited to, any of the following: a biometric recognition model, an image recognition model, or a text recognition model. Under the scenes related to user authority authentication, security protection and the like, the artificial intelligence model is used for extracting biological characteristic data, identifying identity or identifying posture of biological data acquired by the terminal equipment when running in an untrusted execution environment. Wherein the biometric data includes, but is not limited to: biometric data generated based on image data supplied from an image pickup device, or biometric data generated based on fingerprint data supplied from a fingerprint acquisition device. The image data includes face image data, body posture image data, or other image data such as plants and animals. The facial image data includes, but is not limited to, facial feature image data, facial expression image data, and the like. The human pose image data includes, but is not limited to: half-body posture image data with/without occlusion, whole-body posture image data with/without occlusion, and the like. Examples of the identification include: identifying the real identity of a user, identifying the identity preset in the terminal equipment by the user and the like; wherein the true identity comprises an identity provable by the document; the preset identity comprises an identity which can be certified by identity configuration information of the terminal device. For example, an artificial intelligence model runs in an untrusted execution environment to identify the degree of matching of the user's facial feature data with the facial feature data in the identification card. As another example, an artificial intelligence model operates in an untrusted execution environment to identify a degree of match of a user's fingerprint feature data with pre-stored fingerprint feature data. Examples of the gesture recognition include recognizing human expressions, recognizing human static actions, or recognizing human dynamic actions. Such as recognizing blinking, head, lip, etc. movements, recognizing gesture movements, recognizing limb movements, etc.

In order to make the artificial intelligence model and the operation result thereof operated in the untrusted execution environment be regarded as trusted by the business processing task, the business processing task using the artificial intelligence model and the operation result thereof is provided with a corresponding credibility verification result, which can help the business processing task to regard the operation process of the artificial intelligence model and the operation result thereof as having the security level like a PIN code.

To this end, in some examples, a trusted execution environment with a stronger computing power is built into the terminal device to perform the trustworthiness verification. In other examples, the terminal device is externally located with a trusted verification device capable of providing a trusted execution environment. Wherein, the trusted verification device is an external device, which includes but is not limited to: a master device or a slave device connected with the terminal device through a data interface, a remote server, and the like. The trusted verification device can be connected with the terminal device through a wired interface, for example, a USB interface. For example, as a master device, the trusted authentication device may be a portable terminal (e.g., a smart phone, a PAD, etc.) that controls the terminal device in an authentication mode/operation mode, where in the authentication mode, the trusted authentication device performs trust authentication for an artificial intelligence model operating in the terminal device; in the operation mode, the credible verification equipment assists the terminal equipment to execute the business processing task, wherein the business processing task needs to be executed by operating the artificial intelligence model. As another example, as a slave device, the trusted verification device may be an integrated circuit with processing capability (e.g., U-shield, etc.), which performs the trustworthiness verification under the scheduling of the service processing task running in the terminal device. The trusted verification device may also communicate with the terminal device via a network interface, for example, the trusted verification device is a server device in communication with the terminal device, and the trusted verification device performs trusted verification on the artificial intelligence model running in the terminal device by using a communication mechanism.

The trusted execution environment at least comprises a secure operating system (trust OS) running in the terminal equipment, and the secure operating system is used for providing protection measures such as copyright, data security and the like for the running programs. The protection may be in accordance with specifications such as TEE, or other custom protection specifications. The trusted execution environment also includes a first hardware unit that operates under a driving operation of the hardware by the secure operating system. Wherein the first hardware unit may be shared with an untrusted execution environment in the terminal device, or configured separately. For example, the first hardware unit in the trusted execution environment may comprise a separately configured processor or one of a plurality of separate virtual processors in the host processor. As another example, the first hardware unit in the trusted execution environment includes a separate secure memory (e.g., a secure memory in a SIM card), or a separate storage area obtained by configuring a storage device in the terminal device. For another example, the first hardware unit in the trusted environment further includes a network interface for performing network communication in the terminal device and a bus interface for performing internal data transmission, and the various interfaces in the trusted environment implement data transmission under the protection specification on the basis of the corresponding interface protocol.

An untrusted execution environment is configured in the terminal device. The untrusted execution environment comprises at least an Operating System (OS) running in the terminal device alongside a secure operating system (Trusty OS). In other words, the terminal device may be configured with a separate secure operating system (Trusty OS) and Operating System (OS). Examples of the Operating System (OS) include: an IOS-based operating system, an Android-based operating system, a Window-based operating system, or the like. The Operating System (OS) in the terminal device is used to provide basic matters such as managing and configuring memory, determining the priority of system resource supply and demand, controlling the input and output devices of the terminal device, operating the network, and managing the file system for the programs running the business process programs and the artificial intelligence model. The untrusted execution environment further comprises a second hardware unit in the terminal device running under a driving operation of the hardware by the Operating System (OS). Wherein the second hardware unit may be shared with the trusted execution environment or configured separately. For example, the second hardware unit in the untrusted execution environment may comprise a separately configured processor or one of a plurality of separate virtual processors configured to the host processor. For another example, the second hardware unit in the untrusted execution environment includes an independent memory (e.g., a storage device such as a nonvolatile memory or a volatile memory), or another storage area of the storage area in the untrusted execution environment, where the storage device in the terminal device is configured to be read and written. For another example, the second hardware unit in the trusted environment further includes a network interface for performing network communication in the terminal device and a bus interface for performing internal data transmission, and each type of interface in the untrusted environment can perform data transmission according to a corresponding interface protocol.

Taking the configuration of the trusted execution environment in the terminal device as an example, the terminal device includes a storage device and a processing device. Wherein the processing device further comprises a first processing unit and a second processing unit.

The storage device is used for storing an artificial intelligence model, at least one verification execution program and at least one service processing program, and a credibility verification result obtained by executing the verification method. In some examples, the storage device may be configured in trusted and untrusted execution environments depending on the storage rights. For example, the storage device sets higher read-write authority for at least one verification executive program, and five programs with lower read-write authority, such as a service processing program, call any verification executive program when running. In other examples, referring to fig. 1, which shows a schematic structural diagram of a terminal device in some examples, the storage device includes a first storage unit 111 configured in the untrusted execution environment 11 and a second storage unit 121 configured in the trusted execution environment 12. The second storage unit 121 includes the aforementioned secure memory, and may further include a volatile storage medium such as a cache. At least one verification execution program is stored in the second storage unit 121. The first storage unit 111 includes a nonvolatile memory, and may further include a volatile storage medium such as a cache, a memory controller, and the like. The program describing the artificial intelligence model and at least one business process program and the like are stored in the first storage unit 111.

The processing device and the storage device are connected by a communication standard inside a computer such as a bus, wherein, taking fig. 1 as an example, the first processing unit 112 is configured in the untrusted execution environment 11, and is configured to invoke and execute the at least one service processing program, and run the artificial intelligence model in the untrusted execution environment 11 to execute a service processing method; the second processing unit 122 is configured in the trusted execution environment 12 for invoking and executing the at least one verification executive to perform the verification method.

For example, the trusted execution environment is configured in the trusted verification device, please refer to fig. 9, which is a schematic structural diagram of the trusted verification device. Wherein the trusted verification device 3 comprises, configured in a trusted execution environment: interface unit 303, processing unit 302, storage unit 301. The interface unit 303 is at least used for data communication with a terminal device, and includes a serial interface and/or a network interface. The authentication device 3 may comprise only a serial interface, for example a USB interface, to connect the terminal device 1; it is also possible to include only a network interface, such as a SIM card reader, a wifi network interface, to communicate with the terminal device; it may also include a serial interface and a network interface, wherein the terminal device 1 is connected through the serial interface, and communicates with other servers (such as the trusted authentication server 2) through the network interface, and the like. The storage unit 301 may correspond to the second storage unit in the above example, or other memories. For example, the storage unit includes a nonvolatile memory, a volatile memory, and the like. The processing unit 302 may correspond to the second processing unit in the above example, or other processors that can perform data processing and mathematical calculations, such as an FPGA, a CPU, or an integrated circuit including a processor.

In some examples, the terminal device further comprises an acquisition means (not shown) for acquiring biological data; the artificial intelligence model is used for carrying out feature extraction or identification processing on the acquired biological data to obtain data to be processed. The business process and verification process involved in this example will be further detailed later.

For ease of description, the processes subsequently described as being performed by the trusted execution environment under the coordination of the invoked program by the various hardware units within the trusted execution environment are referred to as operations (processes) performed by the trusted execution environment or operations (or processes) run by the trusted execution environment. The processes subsequently referred to as being performed by hardware units in the untrusted execution environment in coordination with the invoked program are referred to as operations (processes) performed by the untrusted execution environment or operations (or processes) performed by the untrusted execution environment.

Here, data is communicated between the untrusted execution environment and the trusted execution environment such that data stored in one execution environment may be processed in another execution environment. For example, a payment program running in an untrusted execution environment executes corresponding payment processing logic by reading security level data stored in a trusted execution environment. As another example, a verifying executive running in a trusted execution environment may perform trust verification by reading data generated by an artificial intelligence model running in an untrusted execution environment.

In order to improve the security of data communication between the untrusted execution environment and the trusted execution environment, namely to prevent the security problems of data leakage, tampering and the like during the data communication between the untrusted execution environment and the trusted execution environment, the terminal device performs security protection on data interacted between the untrusted execution environment and the trusted execution environment. In some examples, data communication between the untrusted execution environment and the trusted execution environment is based on cryptographic techniques. For example, data transferred between the untrusted execution environment and the trusted execution environment is encrypted with a key to secure the data. As another example, a certificate may be utilized to verify data transferred between an untrusted execution environment and a trusted execution environment.

When an artificial intelligence model operated by an untrusted execution environment affects some service processing results, and the service processing results affect security monitoring, account authority, building access control, fund transfer and the like, the artificial intelligence model and the output data thereof need to be trusted. Therefore, the application provides a credibility verification method of the artificial intelligence model. The trusted verification method is applicable to a trusted verification system at least comprising terminal equipment. And the trusted execution environment in the terminal equipment stores at least one verification execution program corresponding to the artificial intelligence model. The at least one verification executive program is used for executing the process of verifying the credibility of the artificial intelligence model operated by the untrusted execution environment in the terminal equipment when the terminal equipment is called to operate.

In some embodiments, the at least one verification execution program is included in a service processing program (APP) of the artificial intelligence model, and is downloaded to the terminal device (or the trusted verification device) along with the service processing program in response to the user downloading operation.

In still other embodiments, the at least one authentication executive may also come from the trusted authentication system, which includes not only the terminal device (or trusted authentication device), but also a trusted authentication server (or called trusted authentication server device).

For convenience of example, the following may be taken as an example of a trusted execution environment built in the terminal device, and it should be noted that the following processes may be performed by software and hardware of a trusted verification device externally connected to the terminal device.

The trusted verification server can be a single server, a server cluster, a distributed server cluster, a cloud server and the like which provide verification execution programs for a plurality of terminal devices configured with artificial intelligence models. Here, according to the actual design, the server is provided by a cloud server provided by a cloud provider. The Cloud Service end comprises a Public Cloud (Public Cloud) Service end and a Private Cloud (Private Cloud) Service end, wherein the Public or Private Cloud Service end comprises Software-as-a-Service (SaaS), Platform-as-a-Service (PaaS), Infrastructure as a Service (IaaS), and Infrastructure as a Service (IaaS). The private cloud service end is used for example for an Aliskian cloud computing service platform, an Amazon cloud computing service platform, a Baidu cloud computing platform, a Tencent cloud computing platform and the like.

In some examples, the trusted authentication server includes an interface device, a storage device, and a processing device. Wherein the interface device is in data connection with the processing device, which may be connected via a bus or via a communication network for data transfer. For this purpose, the interface device includes, but is not limited to, a network card, a mobile network access module, a bus interface connected to the processing device through a bus, a serial interface such as USB, and the like. Each of the interface devices performs data communication through the internet, a mobile network, and a local area network. For example, the interface device of the trusted verification server is in communication connection with an interface device of an artificial intelligence model provider, an interface device of a terminal device, and the like, and the artificial intelligence model provider uploads a program describing an artificial intelligence model data processing relationship to be issued to the trusted verification server through the communicated interface device. And the artificial intelligence model is used for carrying out identity recognition or gesture recognition on the biological data acquired by the terminal equipment during operation. For example, feature extraction is performed on human face features and posture features in the acquired image. In another example, fingerprint feature extraction is performed on the collected fingerprint information. For another example, at least one of the extracted facial features, posture features, or fingerprint features is identified. Also, for example, facial expression recognition is performed on the extracted facial features. For example, the extracted posture features are subjected to posture recognition and the like.

The storage devices include, but are not limited to: Read-Only Memory (ROM), Random Access Memory (RAM), and non-volatile Memory (NVRAM). For example, the storage includes a flash memory device or other non-volatile solid state storage device. In certain embodiments, the storage device may also include memory remote from the one or more processing devices, e.g., network attached memory accessed via RF circuitry or external ports and a communication network, which may be the internet, one or more intranets, Local Area Networks (LANs), Wide Area Networks (WANs), Storage Area Networks (SANs), etc., or a suitable combination thereof. The storage device also includes a memory controller that may control access control to memory by the mobile device's components, such as a Central Processing Unit (CPU) and interface devices, or other components. The storage device stores the program for describing the artificial intelligence model data processing relation received from the interface device and at least one verification execution program corresponding to the artificial intelligence model.

The processing device is connected with the interface device and the storage device and used for calling and executing at least one program so as to coordinate the execution of the interface device and the storage device and send the at least one verification execution program to the terminal equipment provided with the artificial intelligence model. The processing device includes one or more general purpose Central Processing Units (CPUs), one or more application specific processors (ASICs), one or more Digital Signal Processors (DSPs), one or more Field Programmable logic arrays (FPGAs), one or more Graphics Processors (GPUs), or any combination thereof. The processing device is also operatively coupled with an interface device that may enable the processing device to interact with various terminal equipment. For example, the processing device reads the authentication execution program or the like stored in the storage device.

Wherein, the at least one verification executive program is used for performing credibility verification on the artificial intelligence model run by the terminal equipment when being called, and comprises the program obtained by compiling the code and verification configuration information required when the program is executed. The credibility verification is used for verifying the operation process and the operation result of the artificial intelligence model so as to confirm that the artificial intelligence model operated in the untrusted execution environment is honest and not tampered in the operation process, and the operation result is honest, not tampered and not damaged, so that the operation result provided by the artificial intelligence model used when the terminal equipment executes the business processing task conforms to the objective fact.

The verification input data refers to input data required for verifying the artificial intelligence model, and the verification configuration information refers to configuration information related to a type that can be verified by at least one verification execution program, examples of which include at least one of: information related to the result of the verification operation and information related to the operation of the trusted execution environment in the scheduling terminal device. The at least one verification executive program may be determined according to the type of the artificial intelligence model being run, a business processing task for starting the artificial intelligence model, vulnerability easily generated during the running of the artificial intelligence model, and the like, and is used for ensuring that a running result output by the running of the artificial intelligence model is trusted during the business processing. In the business processing tasks such as payment, security protection, account authentication and the like, the verification result is used for providing the credibility basis with the security level data for the operation result output by the artificial intelligence model operating in the untrusted execution environment.

In some examples, the interface device of the trusted authentication server receives at least one authentication execution program corresponding to a certain artificial intelligence model, stores the at least one authentication execution program in the storage device through the processing device, and when the terminal device requests to download a program describing the artificial intelligence model, the processing device reads the corresponding at least one authentication execution program from the storage device and sends the at least one authentication execution program and the program describing the artificial intelligence model to the corresponding terminal device through the interface device.

In still other examples, the processing device selects, based on the artificial intelligence model, at least one verification executive from a set of verification executives that matches the artificial intelligence model.

Here, the artificial intelligence model provider provides not only the program itself describing the artificial intelligence model but also information about the artificial intelligence model. Wherein the related information comprises at least one of: the file information of the uploaded artificial intelligence model, the type of the artificial intelligence model, the input/output data specification, the operating environment and the like. For example, the processing device obtains the program describing the artificial intelligence model and the related information by presenting an interface for uploading the program describing the artificial intelligence model and the related information to a provider. The file information includes, but is not limited to, version information, file header information, and the like. The type of the artificial intelligence model includes, but is not limited to, a type related to a usage scenario, or a type related to an included algorithm, etc. Examples of the types related to the usage scenario include at least one of: a face recognition type, an animal/plant recognition type, an expression recognition type, a gesture recognition type, a character recognition type, and the like. Examples of the types related to the included algorithms include at least one of: CNN algorithm type, markov algorithm type, random forest algorithm type, genetic algorithm type, LSTM algorithm type, etc. Input/output data specifications include, but are not limited to: an input data specification, an output data specification, or a resource occupancy specification, etc. Examples of input data specifications include at least one of: data type, data amount, etc., for example, the input data type includes at least one of: data objects, data object formats, character strings, integer numbers, floating point numbers, and the like. Examples of output data specifications include: data type, data amount, etc., for example, the output data type includes at least one of: data objects, formats of data objects, character strings, integer numbers, floating point numbers, and the like. Examples of the resource occupancy specification include at least one of: memory occupation, external resource types to be called, and the like, wherein the external resource types include at least one of the following: internal resources and authority of the terminal equipment, types of services provided by the internet server side and the like.

And the processing device converts the relevant information into database operation statements, selects at least one storage address of the verification executive program matched with the artificial intelligence model from the database, and acquires each verification executive program. The database is a data management system for the processing device to perform operations such as querying, writing, reading, deleting, and the like on the stored information according to the relevant information, and examples thereof are not limited to: oracle, MySQL, etc. The set of authentication executables may be stored in the storage means of said trusted authentication server or in a storage server communicating with said trusted authentication server, the processing means determining the selected at least one authentication execution utilizing the address link stored in the database and sending the corresponding authentication execution to the terminal device.

In still other examples, the processing device preferentially selects the verification executive from the database, and if the type or number of the selected verification executive does not meet the requirement of the credibility verification, prompts the staff to generate the verification executive which is associated with the relevant information and is absent, and supplements the verification executive to the database and the verification executive set.

It should be noted that the manner of triggering the trusted authentication server to send the corresponding authentication execution program is not only triggered by the download request as described above, but also may be that when the terminal device invokes a service processing program that needs to run an artificial intelligence model, the corresponding service processing task sends out request information for obtaining the corresponding authentication execution program. The request information includes but is not limited to: version information of the artificial intelligence model, terminal equipment information and the like.

Here, the at least one verification execution program includes at least one of: the verification executive program is used for performing operation safety verification on the artificial intelligence model, the verification executive program is used for performing single-operation safety verification on the artificial intelligence model, the verification executive program is used for performing multi-operation safety verification on the artificial intelligence model, or the verification executive program is used for performing integrity verification on the artificial intelligence model.

The operation safety verification refers to verifying the safety of the called resource when the program describing the artificial intelligence model operates the artificial intelligence model because of being called. The resources include, but are not limited to: memory resources of the terminal device, processor resources, software resources installed in the terminal device, and the like.

The single-operation security verification refers to performing security verification on data output by the executed artificial intelligence model based on single input data when the program describing the artificial intelligence model executes the artificial intelligence model due to being called, and includes but is not limited to: verifying the data format of the output data, verifying the numerical value of the output data, etc.

The multi-operation security verification refers to performing security verification on data batch-output by the executed artificial intelligence model based on batch input data when the program describing the artificial intelligence model executes the artificial intelligence model due to being called, and includes but is not limited to: verifying the probability distribution of the batched output data, and the like.

The integrity verification means verifying the integrity of the program file describing the artificial intelligence model and the configuration file thereof, and includes, but is not limited to, verifying the integrity of the program file describing the artificial intelligence model and the configuration file thereof based on a cryptographic technique, where the cryptographic technique includes, for example, a technique of verifying by using a numerical signature, a hash value, or the like corresponding to each file. In some examples, the trusted verification server further generates a second key corresponding to the artificial intelligence model, and the second key is used for being read by the verification executive program and performing the integrity verification. Wherein the second key is a key generated by using a random number and related to a program file and/or a configuration file of the artificial intelligence model.

And the trusted verification server sends at least one verification execution program corresponding to the artificial intelligence model to a secure memory in a trusted execution environment in the corresponding terminal equipment so as to run at the terminal equipment to execute verification operation.

In order to improve the security of data transmission between the trusted verification server and the terminal device, a secure communication channel is established between the trusted verification server and the terminal device. For this purpose, the trusted authentication server may generate or select a first key for secure communication corresponding to the terminal device, and send at least one authentication execution program to the corresponding terminal device using a data transmission mechanism set based on a cryptographic technique. Examples of the data transmission mechanism include: transmitting the encrypted at least one authentication execution program to the corresponding terminal device using a shared key technique/asymmetric key technique; or, at least one verification executive program is sent to the corresponding terminal equipment by using the digital certificate signed by the certification authority. Here, the first key corresponds to the shared key, one of asymmetric keys, a digital certificate, or the like.

At least one authentication executive stored in a secure memory in a trusted execution environment of a terminal device

. The at least one verified execution program stored in the trusted execution environment may be updated to match a version of the artificial intelligence model and/or to prevent at least one verified execution program or verification input information used by the verified execution program from being cracked, corrupted, etc. In some examples, the update procedure required for the update operation may be obtained based on an update period of the trusted verification server and/or a version update of the artificial intelligence model. For example, the trusted execution environment obtains an updated program provided by the trusted verification server and runs the updated program to obtain at least one updated verification execution program. Wherein, in order to ensure the data security of the updating program in the data transmission process, the data communication between the trusted execution environment and the trusted verification service terminal can be executed based on the cryptography technology. For example, the update program is encrypted with a key. As another example, an update program or the like is signed with an approved digital certificate.

The artificial intelligence model running in the untrusted environment is verified for trustworthiness when the trusted execution environment invokes at least one verification executive that is either installed or updated. Here, the at least one verification executive may perform the trustworthiness verification based on the verification initiation step.

In some examples, the at least one verification executive is invoked to execute based on the monitored update operation of the artificial intelligence model, the at least one verification executive performing a trustworthiness verification of the updated artificial intelligence model when invoked by the trusted execution environment. The updating operation of the artificial intelligence model refers to updating the version of the program describing the artificial intelligence model, and comprises updating the program, adding or deleting configuration information of the program, updating program version information and the like.

Here, the trusted execution environment or the untrusted execution environment performs an update operation of monitoring a program describing the artificial intelligence model, and calls the at least one verification execution program when the update operation is monitored. For example, when the untrusted execution environment monitors that the terminal device system is upgraded and/or the version of the program describing the artificial intelligence model installed in the terminal device is updated, a start instruction is sent to the trusted execution environment, and the trusted execution environment calls the at least one verification execution program based on the start instruction to perform credibility verification on the updated artificial intelligence model. For another example, the trusted execution environment monitors version information of a program describing the artificial intelligence model, and when monitoring that the version information changes, calls the at least one verification execution program to perform credibility verification on the updated artificial intelligence model.

In still other examples, a trustworthiness verification of the invoked artificial intelligence model is initiated based on the monitored invoked operation of the artificial intelligence model. The called operation of the artificial intelligence model refers to an operation of calling a program describing the artificial intelligence model according to an instruction to run the artificial intelligence model. The trusted execution environment calls the at least one verification executive when monitoring that the artificial intelligence model is running.

In still other examples, a plausibility verification of the artificial intelligence model is initiated at a preset verification period. The trusted execution environment calls the at least one verification execution program according to a preset verification period and sends an instruction for operating the artificial intelligence model to the untrusted execution environment so as to verify the credibility of the artificial intelligence model. The verification period may be fixed, or a time interval may be set with a start time/an end time of the previous trust verification as a starting point. For example, if the trusted execution environment performs the last execution of the credibility verification according to the update operation of the artificial intelligence model, the time is counted from the end of the last execution according to the time interval of the verification period to determine the starting time of performing the credibility verification again.

It should be noted that the trusted execution environment may initiate the step of verifying the trustworthiness according to at least one of the above-mentioned initiation manners.

The execution process of the initiated credibility verification comprises the following steps: and in the trusted execution environment, performing credibility verification on the artificial intelligence model running in the untrusted execution environment to obtain a credibility verification result. Wherein the credibility verification information includes but is not limited to: software in the untrusted execution environment, occupation information of hardware resources during the operation of the artificial intelligence model, temporary data and/or output data generated during the operation of the artificial intelligence model, and the like.

In some examples, the trusted execution environment initiates a trustworthiness verification operation upon execution of the artificial intelligence model, which takes data that the artificial intelligence model needs to input at runtime as verification input data, and obtains corresponding trustworthiness verification information.

In other examples, the trusted execution environment may further output various types of validation input data for the trustworthiness validation to the untrusted execution environment, causing the artificial intelligence model to run in the untrusted execution environment, thereby obtaining corresponding trustworthiness validation information.

The method of initiating, verifying multiple sources of input data, and the various types of trust verification operations described in the examples above, the trust verification operations including at least one of:

please refer to fig. 2, which is a flowchart illustrating a process of performing the operation security verification. In step S110, the artificial intelligence model is run in the untrusted execution environment using the first verification input data extracted from the trusted execution environment, resulting in a first running result. In step S120, a security verification is performed on the first operation result in the trusted execution environment.

In this case, the first authentication input data is stored in advance in the trusted execution environment and is used for the operational security authentication of the artificial intelligence model. When the operation security verification is executed, first verification input data are read by a trusted execution environment and are transmitted to an untrusted execution environment so that an artificial intelligence model processes the first verification input data; the untrusted execution environment transmits a first operation result generated during the operation of the artificial intelligence model to the trusted execution environment, and the trusted execution environment performs operation security verification on the first operation result. The running period of the artificial intelligence model comprises the running start, the running process and the running end, and correspondingly, the first running result comprises running information generated at any moment in the running period. Wherein the first operational result comprises at least one of: the running result related to the memory occupation or the running result related to the external program request. Examples of the operation result related to the memory usage include operation information about whether the memory occupied during the operation of the artificial intelligence model overflows or not. Examples of the operation result related to the request external program include request information, interception information, and the like of the request external program generated during the operation of the artificial intelligence model. For example, the artificial intelligence model generates request information for establishing communication with a server in the internet during operation; for another example, the artificial intelligence model generates request information for starting other services in the terminal device during operation, or generates monitoring information for monitoring a preset function port of the terminal device, and the like. And the trusted execution environment performs operation security verification on the acquired first operation result according to the execution logic of each verification execution program corresponding to the operation security verification type. For example, a first operation result indicating that the memory is not overflowed is determined as a verification result that the operation safety is qualified. For another example, whether the IP address of the server in the request message in the first operation result is in the white list/black list is analyzed, and the verification result that the operation security is qualified/unqualified is determined according to the analysis result. And for another example, analyzing the monitoring authority of the monitoring information in the first operation result, and determining the verification result of qualified/unqualified operation safety according to the analysis result.

Please refer to fig. 3, which is a flowchart illustrating the operability verification. In step S210, the artificial intelligence model is operated in the untrusted execution environment by using at least one second verification input data extracted from the trusted execution environment, and second operation results corresponding to the second verification input data are output. In step S220, in the trusted execution environment, performing operability verification on each second operation result.

Here, second verification input data is stored in the trusted execution environment and is used to verify the operability of the artificial intelligence model. When operability verification is executed, second verification input data are read by the trusted execution environment and are transmitted to the untrusted execution environment so that the artificial intelligence model processes the second verification input data; and the untrusted execution environment transmits a second operation result generated during the operation of the artificial intelligence model to the trusted execution environment, and the trusted execution environment performs operability verification on the second operation result. Wherein the operability verification comprises: single operational security verification and multiple operational security verification. Wherein the second verification input data may be the same verification input data or different verification input data as the first verification input data mentioned in the example of fig. 2. The second operation result is an operation result output after the artificial intelligence model performs data processing on the second verification input data, and the second operation result outputs a corresponding operation result according to the data type processed by the artificial intelligence model and the integrated function; the second operational result includes at least one of: the operation result related to the data format and the operation result related to the numerical value are obtained, wherein the data format includes formats such as a boolean type, a character string type, a numerical value type or a custom type, and the numerical value includes an integer numerical value, a floating point numerical value and the like. For example, when the artificial intelligence model is operated to perform identity verification on a face in image data, the output operation result is the confidence level that the identity of the face is verified to be user a or not user a, or the output operation result is the confidence level that the identity of the face is verified to be user a, user B, and user C, respectively.

During the single-operability security verification, the step S220 includes matching a second operation result generated during a single operation of the artificial intelligence model with a pre-stored target operation result, so as to determine whether the artificial intelligence model is operable according to the corresponding matching result. And taking a second operation result generated by the single operation of the artificial intelligence model as a confidence coefficient a for recognizing the human body posture in the image data as the posture A, analyzing whether the confidence coefficient a% and a prestored target operation result a '% are within a preset error range by a trusted execution environment, if the confidence coefficient a% and the prestored target operation result a'% are within the preset error range, determining that the matching result is operable, otherwise, determining that the matching result is not operable. And taking a second operation result generated by the single operation of the artificial intelligence model as a posture B for recognizing the human posture in the image data, comparing whether the human posture B is consistent with a pre-stored target operation result B' or not by the trusted execution environment, if so, determining that the matching result is operable, otherwise, determining that the matching result is not operable. For another example, the trusted execution environment detects whether the number of bits, the data type, and the like of the second operation result are matched with the target operation result, and if so, determines that the matching result is operable, otherwise, determines that the matching result is not operable.

During the multi-operability security verification, the trusted execution environment inputs the stored second verification input data into the artificial intelligence model operated by the untrusted execution environment, so that the artificial intelligence model performs batch processing, and correspondingly, the step S220 includes counting distribution of second operation results generated when the artificial intelligence model operates in batch; and determining whether the artificial intelligence model is operable according to the similarity between the statistical distribution result and the expected distribution. Wherein the expected distribution may be fixed in advance, or determined based on a statistically pre-stored target operation result. For example, the expected distribution is obtained by the trusted execution environment counting target operation results corresponding to the second verification input data.

Taking an artificial intelligence model for testing security monitoring as an example, a trusted execution environment inputs a plurality of stored second verification input data for simulating security monitoring diversity into an artificial intelligence model operated by an untrusted execution environment, the artificial intelligence model outputs a second operation result corresponding to each second verification input data during batch processing, and feeds the second operation result back to the trusted execution environment, the trusted execution environment counts the second operation data according to a plurality of event types related in a security monitoring scene to obtain probability distribution of the artificial intelligence model in processing the security monitoring scene, similarity matching is performed between the obtained distribution result and expected distribution, if the similarity is within a preset error range, the matching result is determined to be operability, otherwise, the matching result is determined to be no operability. The event types related in the security monitoring scene are related according to the monitored security scene, for example, the security scene is public places such as roads and shops, and the event types include at least one of the following: a violent event type, a theft event type, an illegal/violation event type, etc. For another example, if the security scene is a four-person place such as a house, the event type includes at least one of the following: a theft event type, a pet event type, a human emergency event type, etc.

It should be noted that the above example may also be applied in an account authentication scenario such as terminal payment and account login. Taking an artificial intelligence model for testing terminal payment as an example, a trusted execution environment inputs second verification input data of a plurality of pieces of fingerprint information stored for simulating terminal payment into an artificial intelligence model operated by an untrusted execution environment, the artificial intelligence model outputs second operation results corresponding to the second verification input data during batch processing execution and feeds the second operation results back to the trusted execution environment, the trusted execution environment counts the second operation data according to a plurality of event types related to a terminal payment scene to obtain probability distribution of the artificial intelligence model in the terminal payment scene, similarity matching is performed between the obtained distribution results and expected distribution, if the similarity is within a preset error range, the matching results are determined to be operability, otherwise, the matching results are determined to be no operability. The event types related to the terminal payment scene comprise: successful person/company/parent-child account matching, failed person/company/parent-child account matching, successful payment, failed payment, status of funds transfer, etc.

The target operation result mentioned in each of the above examples may be from each operation result that passes the credibility verification in the history verification operation of the terminal device, or from the verification server. In some examples, the trusted execution environment saves the results of the verified and trusted execution of the past execution and its input data, and performs the operational verification as the target results of the execution and its second verification input data. In still other examples, the trusted execution environment counts the results of verified trusted runs of past runs and their input data and obtains an expected distribution for use in performing operational verification. In still other examples, the trusted execution environment obtains second verification input data and target execution results thereof from a verification service.

By using the above obtaining manner of each example, the target operation result includes at least one of the following: verified second operation results obtained when the operability verification is performed by the artificial intelligence model over the course of time; a verified second run result obtained by the historical version of the artificial intelligence model when performing the operability verification; or a verified second operation result obtained when performing the operability verification by another artificial intelligence model of the same kind as the artificial intelligence model. For example, the trusted execution environment takes a second operation result with operability verification in previous credibility verification of the artificial intelligence model of the same version as a target operation result, and takes input information corresponding to the target operation result as second verification input information, so as to be used in subsequent same-class operability verification of the artificial intelligence model of the version. For another example, the trusted execution environment takes a second operation result with operability verification in previous credibility verification of artificial intelligence models of different versions as a target operation result, saves input information corresponding to the target operation result as second verification input information, and selects the corresponding second verification input information and the target operation result thereof from the stored second verification input information and the target operation result thereof according to the relevant verification configuration information for the current version to execute the operability verification of the current version. For another example, the target operation result obtained by the trusted execution environment is provided by the verification server, where the target operation result provided by the verification server is a verified second operation result obtained when the verification server performs the operability verification on the artificial intelligence model or another artificial intelligence model similar to the artificial intelligence model, and the verification method of the second operation result is the same as or similar to the verification method performed by the terminal device, and is not described in detail here.

Please refer to fig. 4, which is a flowchart illustrating an integrity verification process. In step S310, data communication between the trusted execution environment and the untrusted execution environment is established. In step S320, integrity verification is performed on each file required for running the artificial intelligence model based on a cryptographic technique in the trusted execution environment.

The process of establishing data communication may be a separate step or steps performed by the trusted execution environment during integrity verification to read information associated with files stored in the untrusted execution environment. Wherein, the information related to each file includes but is not limited to: file signatures, certificates, etc. For example, each file required for running the artificial intelligence model is configured with each file signature, a key for verifying the file signature is prestored in the trusted execution environment, the trusted execution environment reads each file signature, each signature is analyzed by using the key to obtain version information, file header information and other information which can be used for detecting the integrity of the artificial intelligence model, and each analyzed information is matched with each file to obtain a verification result of the integrity of the corresponding file.

It should be noted that any of the above examples of performing trust verification may be performed simultaneously or sequentially. For example, operability verification and operational security verification may be performed synchronously during the artificial intelligence performance model run. The various examples of trust verification described above may be initiated using different policies. For example, integrity verification may be performed only at first install or version update. As another example, all types of trustworthiness verification may be performed using a predetermined periodicity or artificial intelligence model runtime. The examples of trustworthiness verification described above are not necessarily all configured in the terminal device, and the trusted execution environment may identify the artificial intelligence model as trustworthy through any one or more types of trustworthiness verification.

It should be noted that at least one of the above examples of the credibility verification may implement credibility verification on the artificial intelligence model during the operation of the artificial intelligence model by a certain business processing task in the terminal device. In other words, during the execution of the artificial intelligence model in an untrusted execution environment, the following steps are performed in the trusted execution environment: and reading credibility verification information provided by the artificial intelligence model from the untrusted execution environment, and performing credibility verification on the artificial intelligence model according to the credibility verification information to obtain a credibility verification result. The service processing task is a service logic executed when a service processing program in the terminal equipment is called; and the business processing task starts an artificial intelligence model to input data related to business processing into the artificial intelligence model, obtains an operation result provided by the artificial intelligence model, and executes subsequent business logic by utilizing the operation result business processing task.

In some examples, the business processing task performs unlocking operation of the terminal screen by using operation of the artificial intelligence model, coordinates a collecting device of the terminal equipment to obtain biological characteristic data of a user, starts to operate the artificial intelligence model so as to identify the biological characteristic data, and performs unlocking/unlocking operation according to an operation result output by the artificial intelligence model; the trusted execution environment determines that the untrusted execution environment runs the artificial intelligence model by monitoring the task list of the terminal device, obtains credibility verification information provided during the running of the artificial intelligence model, and performs credibility verification on the obtained credibility verification information by using the modes provided by the examples. The example of the operation safety verification includes verifying whether a memory in the credibility verification information overflows or whether a data format conforms to a preset format, and the like, the example of the operability verification includes verifying whether a data type of an operation result in the credibility verification information conforms to the preset format or whether a numerical value is within a preset range or whether distribution of the operation result of the statistical cumulative operation conforms to expected distribution, and the example of the integrity verification includes checking whether information in each file signature required by the currently operated artificial intelligence model conforms to related information of each file, and the like.

According to the above-described credibility verification method in each example, the following examples are given as examples of the process of performing credibility verification on an artificial intelligence model running on a certain terminal device: a provider of an artificial intelligence model uploads a program describing the artificial intelligence model to be issued and related information of the artificial intelligence model to a trusted verification server in advance so that a technician can generate at least one verification execution program, wherein the at least one verification execution program is issued at the trusted verification server; after the program describing the artificial intelligence model is released, a user installs the program describing the artificial intelligence model in an untrusted execution environment of a terminal device by using a program installation operation, wherein the program installed in the terminal device further comprises a business processing program, and the business processing program executes a business processing task when running, wherein the business processing task not only calls the program of the artificial intelligence model to run the artificial intelligence model in the execution process, but also needs to acquire a verification result of the artificial intelligence model to confirm that the running result provided by the artificial intelligence model is trustable, therefore, based on a reading request of the business processing task, the trustable execution environment of the terminal device establishes safe data communication with a trustable verification service terminal based on a cryptography technology, and acquires and runs at least one verification execution program corresponding to the artificial intelligence model from the trustable verification service terminal to execute trustable verification, until various types of verification results of the credibility verification are obtained. The way in which the trustworthiness verification is performed may be as described in the foregoing examples and will not be described in detail here. And the service processing task determines to continue executing/exiting the current task according to the obtained verification result.

As can be seen from the above examples relating to data security using cryptography, in order to acquire and run at least one authentication execution program in cooperation with a terminal device, the trusted authentication server further manages a first key used for secure communication transmission of the at least one authentication execution program, and/or a second key required for integrity authentication of the artificial intelligence model.

The first key and the second key can be used alternatively or both according to a preset communication mode between the trusted verification server and the terminal device and a verification type configured for the credibility verification of the corresponding artificial intelligence model. The trusted verification server can update each key by managing the validity period of each key, or update each key according to the period of database turnover. The credible verification server can also obtain the running frequency of various artificial intelligence models according to the data communication with the terminal equipment, so as to determine the artificial intelligence models which are not used any more, the version information and the like thereof, and delete or invalidate the corresponding keys according to the determined version information of the artificial intelligence models which are not used any more. The credible authentication server side further generates a corresponding first key and/or a second key according to the updated version (or the new artificial intelligence model) uploaded by the provider of the artificial intelligence model and each piece of relevant information of the updated version. Thereby realizing dynamic management of various keys.

It should be noted that the trusted verification service side may also manage other keys related to the trustworthiness verification, for example, a key required for data transmission between a trusted execution environment and an untrusted execution environment inside the terminal device. The management of these other keys by the trusted authentication server is considered as one of the ways of dynamically managing the various keys under the technical framework of the trust authentication provided in the present application, and is the same as or similar to the way of managing the first key and the second key, and will not be described in detail herein.

The computer devices participating in the business processing task can confirm the credibility of the operation result output by the artificial intelligence model according to the credibility verification result obtained by utilizing various credibility verifications, in other words, the credibility verification result is used for providing verification information that the corresponding artificial intelligence model is credible/incredible for the executed business processing task. Here, the computer device may be the terminal device, or may be a server device that communicates with the terminal device. The service end device may include various functions provided by the verification service end, and may also be a separate service device for cooperating with the terminal device to complete a service processing task, or a computing device of another terminal or service end for cooperating with the terminal device to complete a service processing task. Taking an example that a trusted execution environment of the terminal device stores a trusted verification result, the untrusted execution environment of the terminal device confirms the trusted verification result during execution of a service processing task; or the trusted execution environment sends the credibility verification result to business processing server equipment communicated with the terminal equipment, and the business processing server equipment executes confirmation operation so that the business processing task can perform subsequent processing on the operation result of the artificial intelligence model when confirming that the credibility verification result is trusted. Taking an example that a trusted execution environment of a verification device stores a trusted verification result, the verification device sends the trusted verification result to a terminal device, so that the terminal device confirms the trusted verification result; or the verification equipment sends the credibility verification result to service processing server equipment communicated with the terminal equipment, and the service processing server equipment executes confirmation operation so that the service processing task can perform subsequent processing on the operation result of the artificial intelligence model when confirming that the credibility verification result is credible.

Please refer to fig. 5, which is a flowchart illustrating a business process performed by using the trust verification result. Specifically, in step S410, during the operation of the service processing task by the terminal device, the artificial intelligence model is operated in the untrusted execution environment to obtain the data to be processed. In step S420, in a state that the credibility verification result of the artificial intelligence model is confirmed to be credible, the data to be processed is used to execute the business processing task; the trustworthiness verification result is from the trusted execution environment.

Here, the terminal device executes a certain service processing task according to the current device state, or executes a certain service processing task according to the monitored event of the user operation. During the operation of the service processing task of the terminal equipment, the service processing task instructs an untrusted execution environment in the terminal equipment to operate an artificial intelligence model which is tested by credibility verification, an operation result is obtained based on the operated artificial intelligence model, and data to be processed is obtained based on the operation result; the data to be processed needs to be processed continuously under the condition that the credibility verification result of the corresponding artificial intelligence model stored in the credible execution environment is confirmed to be credible, so as to complete the corresponding business processing task. The data to be processed can be an operation result, which indicates that the data output by the artificial intelligence model is to be subsequently processed by the task to be processed; the data to be processed may be intermediate data in the execution process of the service processing task, which is obtained after the service processing task performs subsequent processing on the operation result.

In some examples, the manner of confirming the credibility verification result in the step S420 includes: during execution of the business processing task, validating the trustworthiness verification results read from the trusted execution environment in the untrusted execution environment to validate that the executed artificial intelligence model is trustworthy; and executing data processing operations in the business processing task on the data to be processed in the untrusted execution environment.

Taking the service processing task as a screen unlocking task as an example, when the terminal device is in a screen locking state, the untrusted execution environment of the terminal equipment starts an unlocking task and monitors biological data provided by a camera device or a fingerprint acquisition device of the terminal equipment, the unlocking task inputs the biological data into an artificial intelligence model when receiving the biological data so as to obtain an operation result whether the biological data is matched with a preset biological characteristic or not, the operation result is used as the data to be processed, when the business processing task executes the subsequent task of unlocking/maintaining the lock screen by using the data to be processed, the result of the authenticity verification stored in the trusted execution environment of the terminal device is also read for confirmation, when the credibility verification result shows that all kinds of credibility verification of the artificial intelligence model are credible, the business processing task executes unlocking operation, namely switching a display interface of the terminal equipment from a screen locking interface to an unlocking interface (such as a desktop interface and the like); otherwise, the screen locking interface is maintained or a warning prompt is given.

It should be noted that the above unlocking example is only an example, and in fact, any service processing task completely executed by the terminal device may be used to confirm the credibility verification result in any link before processing the operation result of the artificial intelligence model in the service processing task, before operating the artificial intelligence model, or before completing the service processing task, so that the artificial intelligence model and the operation result thereof have credibility of the security level data. The example of the service processing task suitable for the above operation further includes: the service processing tasks of plant identification class and the service processing tasks of mobile phone system account authentication class.

In other examples, the manner of confirming the credibility verification result in step S420 includes: and sending the credibility verification result to server equipment in the service processing system so that the server equipment can confirm the credibility verification result.

Still taking the above-mentioned unlocking task as an example, at any time when the unlocking task is not executed yet, the credibility verification result in the trusted execution environment is sent to the server side device, and the confirmation information fed back by the server side device is obtained, if the confirmation information is credible, the unlocking task is continuously executed in a credible state, otherwise, the screen locking state is maintained.

Taking the business processing task as an example of a payment task, the terminal device executes a payment task of transferring the payment amount c in the fund account P of the user to the fund account Q under the payment operation of the user, receives biological data provided by a camera device or a fingerprint acquisition device of the terminal device when the payment task is executed, inputs the biological data into an artificial intelligence model to obtain extracted biological characteristic information, and sends the biological characteristic information to the server device, so that the server device performs characteristic matching and determines the fund account P corresponding to the biological characteristic information, and executes a subsequent payment task of transferring the payment amount c in the fund account P to the fund account Q. Before feature matching is carried out on the server side equipment or before transfer operation is carried out on the server side equipment, a credibility verification result in a credible execution environment in the terminal equipment is obtained and confirmed, and when the credibility verification result shows that all kinds of credibility verification of the artificial intelligent model are credible, a service processing task carries out subsequent feature matching operation or carries out transfer operation; otherwise, giving a transfer failure prompt or a matching failure prompt and the like.

It should be noted that the above-mentioned confirmation manner is only an example, and the confirmation manner may also be performed in the terminal device, similar to the unlocking example, and is not described in detail here.

It should be further noted that the above payment example is only an example, and in fact, any business processing task cooperatively executed by using the terminal device and the server device may use any link in the business processing task before processing the operation result of the artificial intelligence model, before operating the artificial intelligence model, or before completing the business processing task to confirm the credibility verification result, so that the artificial intelligence model and the operation result thereof have credibility of the security level data. The example of the service processing task suitable for the above operation further includes: security monitoring service processing tasks, entrance guard service processing tasks, remote account authentication service processing tasks and the like.

It should be further noted that the step of confirming the result of the authenticity verification in the above example may also be performed in an untrusted execution environment of the terminal device.

In addition, on the one hand, in order to ensure security of data communication between a server device and a terminal device during data communication, at least when a result of authenticity verification is transmitted, the step of transmitting the result of authenticity verification to the server device includes: and sending the credibility verification result to the server side equipment by utilizing the safe data communication between the credible execution environment and the server side equipment. For example, the trusted execution environment and the server device transmit the credibility verification result by using a shared key manner. For another example, the trusted execution environment and the server device transmit the trust verification result by using the authenticated digital certificate.

On the other hand, in order to ensure that various data required by a service processing task including data to be processed transmitted between the terminal device and the server device are safe, during the execution of the service processing task, the service processing method further comprises the step of encrypting the data including the data to be processed related to the service processing task.

The process of executing the service processing task by the service processing system comprising the terminal device and the server device is described by taking the example of encrypting the data to be processed and executing the subsequent service task by using the encrypted data to be processed.

In some specific examples, the manner in which the terminal device encrypts the to-be-processed data obtained based on the operation result of the artificial intelligence model includes encrypting the to-be-processed data by using a key, and sending the encrypted to-be-processed data to the server device, so that the server device performs a data processing operation in the business processing task by using the encrypted to-be-processed data. The key may be a shared key between the terminal device and the server device, or may be an asymmetric key. And by using the key, the server-side equipment obtains the data to be processed through decryption operation, and performs subsequent processing on the data to be processed to complete the service processing task.

In some specific examples, the encryption processing method includes: dispersing the data to be processed into N data fragments to be processed; wherein N is more than 1. Here, the dispersion method may be a random number summation method. For example, X1 and X2 are randomly generated, and dividing the data to be processed into X into three pieces of data to be processed are X1, X2, and (X-X1-X2), respectively. The dispersion mode can also be dispersion processing based on a Shamir dispersion algorithm, wherein the number N of the dispersions is more than or equal to the minimum number Kmin of fragments required for recovering the data to be processed, and N is more than or equal to Kmin. The number N of the distributed data fragments is larger than the minimum number Kmin, so that the recovery of the data to be processed is not influenced when the abnormal condition of part of computing equipment for processing/storing the data to be processed fragments occurs, and further the execution of the whole service processing task is not influenced.

The process of executing the subsequent business processing task by using the dispersed N data slices to be processed by using the dispersed processing mode comprises the following steps: and sending at least part of the data fragments to be processed to a multi-party security computing system which is communicated with the service processing system, so that the multi-party security computing system can execute the service processing task on each data fragment to be processed based on a multi-party security protocol.

The Multi-Party Secure computing system performs data processing on a part of business processing tasks by means of Secure Multi-Party computing (Secure Multi-Party computing) by using a plurality of computing nodes, so as to solve the problem of securely computing an agreed data processing without a trusted third Party.

The computing nodes in the multi-party secure computing system may be a single computer device, or a physical device or a virtual device used in a cloud architecture-based service system. The single computer device may be an autonomously configured computer device that can execute the business processing task, and may be located in a private computer room or a leased computer location in a public computer room. The computing node may also be a computer device in a business service system, for example, the computing node is a terminal device and/or a server device. For example, at least one computer device in the server device is at least one computing node in a multi-party secure computing system. In addition, the form and the set geographical position of the physical or virtual device of the computing node are not limited. For example, the compute nodes may be located on different virtual devices of the same physical server and managed separately by administrative authority. The service system of the cloud architecture comprises a public cloud service end and a private cloud service end, wherein the public or private cloud service end comprises SaaS, PaaS, IaaS and the like. The private cloud service end comprises an Array cloud computing service platform, an Amazon cloud computing service platform, a Baidu cloud computing platform, a Tencent cloud computing platform and the like. The virtual device may be one of devices in which an entity server virtualizes a single device into multiple logical devices through a virtualization technology, and the multiple logical devices are used by multiple service processing tasks at the same time.

The multi-party security protocol is a computing protocol which is set according to the number of computing nodes participating in the multi-party security computing system and used for coordinating the computing nodes to execute rules of mathematical computation, logic computation, data transmission computation and the like. For example, a multi-party security protocol is a computing rule set using up to four computing nodes and employing a secret sharing algorithm, which includes but is not limited to: including addition, subtraction, multiplication, bit extraction, inadvertent transmission, etc. Wherein, each computing node utilizes the shared random number to execute local computation so as to obtain intermediate data or computation results for cancellation.

Taking the example of using four computation nodes to cooperatively compute multiplication of two numbers, the first computation node and the second computation node are made to share a random number r₁₂And r'₁₂And having said third and fourth computing nodes share a random number r_abAnd r'_ab(ii) a The first computing node and the second computing node respectively carry out multiplication computation on the private data groups held by the first computing node and the second computing node and are used for offsetting the random number r₁₂And r'₁₂So that the first computing node gets the intermediate data t₁And t'₁And the second computing node obtains the intermediate data t₂And t'₂(ii) a The third computing node and the fourth computing node respectively carry out multiplication computation on the private data groups held by the third computing node and the fourth computing node and are used for offsetting the random number r_abAnd r'_abSo that the first computing node gets the intermediate data t_aAnd t'_aAnd the second computing node obtains the intermediate data t_bAnd t'_b(ii) a Causing the first compute node and the third compute node to permute a respective one of the intermediate data, and the first compute node and the fourth compute node to permute a respective one of the intermediate data; causing the second compute node and the third compute node to permute a respective one of the intermediate data, and the second compute node and the fourth compute node to permute a respective one of the intermediate data; and enabling each computing node to perform local computation including addition by using the intermediate data paired based on the permutation operation, so that each computing node obtains two computation results including the cancelable random numbers.

For example, the number X is dispersed into { X in advance₁,x₂And { x'₁,x′₂}; the number Y is dispersed into Y₁,y₂And { y'₁,y′₂}. Having the first computing node execute a program based on the formula t₁＝x₁×y’₁-r₁₂And t'₁＝x’₁×y₁-r’₁₂And obtaining intermediate data t₁And t'₁(ii) a And having the second computing node proceed based on formula t₂＝x₂×y’₂+r₁₂And is based on the formula t'₂＝x’₂×y₂+r’₁₂Obtaining intermediate data t by local calculation₂And t'₂. Wherein r is₁₂And r'₁₂Is a shared random number between the first compute node and the second compute node.

It should be noted that, the above-mentioned manner of making the first computing node subtract the random number and making the second computing node add the random number is only an example, and a manner of making the first computing node add the random number and making the second computing node subtract the random number may also be used.

Having the third computing node execute a function based on formula t_a＝x_a×y’_a-r_abAnd is based on the formula t'_a＝x’_a×y_a-r’_abObtaining intermediate data t by local calculation_aAnd t'_a(ii) a And having the fourth computing node execute a function based on formula t_b＝x_b×y’_b+r_abAnd is based on the formula t'_b＝x’_b×y_b+r’_abObtaining intermediate data t by local calculation_bAnd t'_b. Wherein r is_abAnd r'_abIs a shared random number between the first compute node and the second compute node.

It should be noted that the above-mentioned method of making the third computing node subtract the random number and making the fourth computing node add the random number is only an example, and a method of making the third computing node add the random number and making the fourth computing node subtract the random number may also be used.

Let the first computing node intermediate data t₁Is sent toA fourth compute node, and t 'intermediate data'₁Sending to a third computing node; let the second computing node intermediate data t₂Sending to a third compute node, and sending intermediate data t'₂Sending the data to a fourth computing node; let the third computing node send the intermediate data t_aSending to a second compute node, and sending intermediate data t'_aSending the data to a first computing node; and having the fourth computing node to convert the intermediate data t_bSending to the first compute node, and sending the intermediate data t'_bAnd sending the data to the second computing node.

It should be noted that the above replacement manner is set according to the multi-party multiplication calculation, and the replacement manner may be adaptively adjusted according to the multiplication local calculation executed by the actual calculation node, which is not illustrated herein.

Having the first compute node execute based on the formula z₁＝t₁+t_bAnd z'₁＝t’₁+t’_aObtaining a calculation result z₁And z'₁(ii) a The second computing node performs a calculation based on the formula z₂＝t₂+t_aAnd z'₂＝t’₂+t’_bObtaining a calculation result z₂And z'₂(ii) a Third computing node execution based on formula z_a＝t_a+t₂And z'_a＝t’_a+t’₁Obtaining a calculation result z_aAnd z'_a(ii) a The fourth computing node performs a function based on the formula z_b＝t_b+t₁And z'_b＝t’_b+t’₂Obtaining a calculation result z_bAnd z'_b。

Here, the calculation results obtained by the first and second calculation nodes, and the third and fourth calculation nodes may be restored to the calculation result of X times Y. For example, (z)₁+z₂) Is the result of the X by Y calculation.

Taking the k-th digit in the binary number of the number X cooperatively extracted by four computing nodes as an example, the step of enabling each computing node to respectively perform local computation on the respective acquired data group and interacting intermediate data generated by the local computation to obtain computation results respectively held by each computing node includes: the four computing nodes obtain respective supporting computing results by utilizing data interaction of k rounds of 1-bit replacement data, wherein the computing results are used for extracting binary bits in the data X; k is the number of binary bits to be extracted corresponding to the data X. Wherein, the data set is obtained by dispersing the data X.

For example, a first compute node, a second compute node, a third compute node, and a fourth compute node in the multi-party secure computing system obtain a data set { x } in sequence₁Data set { x }₂Data set { x }_aAnd a data set { x }_b}; wherein, { x₁,x₂,x_a,x_bAnd the data X is subjected to random dispersion processing to obtain binary-representation private data, wherein each data group and the data X have the same binary digit number k. The multi-party secure computing system performs the steps of:

each compute node initializes a bit value for output { c }₁,c’₁}，{c₂,c’₂}，{c_a,c’_a}，{c_b,c’_b}; and enabling the first computing node and the second computing node to share a random number r₁₂And b₁₂(ii) a And making the third computing node and the fourth computing node share a random number b_ab(ii) a Wherein the random number r₁₂、b₁₂And b_abIs a binary random number generated based on the number of extracted bits k.

The first computing node and the second computing node use the random number r₁₂For respectively held private data x₁And x₂Performing logic processing on the kth bit to obtain the uniform binary intermediate data u with the kth bit₁And u₂。

Let the first computing node intermediate data u₁Sent to the third computing node and processed by the third computing node based on the formula u₁∧x_aIs logically calculated and obtainedIntermediate data u_a。

Based on the k value, the following loop calculation is set: each computing node is used for generating private data x₁With the random number b based on the sharing₁₂Or b_abAnd obtaining the intermediate data of the ith round; performing replacement processing on the intermediate data obtained in each turn, and assigning corresponding output bits; the first computing node and the third computing node perform replacement processing on the intermediate data, and the second computing node and the fourth computing node perform replacement processing on the intermediate data;

and each computing node utilizes the assigned output bit and the random number to carry out logic computation on the k bit value of the private data held by each computing node to obtain a computing result.

The first computing node is to compute result c'₁To a third computing node; the second computing node will compute result c'₂To a fourth computing node; the third computing node will compute the result c_aTo a second computing node; the fourth computing node calculates the result c_bProvided to the first compute node so that each compute node holds two compute results. The calculation result of each calculation node can be restored to the binary digit number of the extracted k-th digit.

Taking the example of cooperative and inadvertent transmission of data X by using four computing nodes, enabling the four computing nodes to perform local computation and data interaction based on a sharable random bit value used for representing transmission/non-transmission data C, and obtaining respective computation results; wherein the calculation result comprises a result for indicating that the corresponding data X is transmitted or a result for indicating that the corresponding private data X is not transmitted.

For example, the arrays composed of the fragments of the data X obtained by each computing node and processed in a scattered manner are sequentially { X }₁,x’₁}，{x₂,x’₂}，{x_a,x’_a}，{x_b,x’_b}; in other words, data { x₁,x’₁,x₂,x’₂,x_a,x’_a,x_b,x’_bObtaining data X through random dispersion processing; each computing node obtains sharable random bit value { c) set based on private data to be shared respectively₁,c’₁}，{c₂,c’₂}，{c_a,c’_a}，{c_b,c’_b}; the multi-party secure computing system performs the steps of:

enabling the first computing node and the second computing node to share a first random number r₁₂And r'₁₂(ii) a The first computing node and the third computing node share a second random number r'_1a(ii) a The first computing node and the fourth computing node share a second type of random number r_1b(ii) a Enabling the second computing node and the third computing node to share a second type random number r_2a(ii) a The second computing node and the fourth computing node share a second random number r'_2b(ii) a Enabling the third computing node and the fourth computing node to share a first type of random number r_abAnd r'_ab。

And enabling each computing node to perform mathematical computation with a first type of random number on whether the array is transmitted or not by using the respectively configured bit value, and performing mathematical computation with a second type of random number on whether the first type of random number is transmitted or not by using the respectively configured bit value to obtain intermediate data and an intermediate random number.

And the first computing node and the second computing node respectively perform the replacement operation of the intermediate data and the intermediate random number with the third computing node and the fourth computing node.

And enabling each computing node to execute mathematical computation including the cancellation of the second random number, and obtaining the respective held computation result. The computation results held by the computation nodes can be restored to the transmitted data X or null.

Under the multi-party secure computing protocol of the multi-party secure computing system comprising four computing nodes mentioned above, more optimized mathematical or logical computations with more complex execution can be obtained. And will not be described in detail herein. In addition, a multi-party secure computing system comprising four computing nodes does not have to perform computations with four computing nodes, for example, addition and subtraction computations may use two or three of them for multi-party secure computations.

Based on the above example of the multi-party security protocol executed by the multi-party security computing system comprising four computing nodes, part of the data processing in the business processing task can be executed by the multi-party security computing system. For example, part of the business processing tasks which are completed by the terminal device or the server device are handed to the multi-party security computing system to be executed. Therefore, intermediate data/service processing results and the like of the service processing task have high safety, and the problem that private data is easy to leak by a single computing device is effectively solved.

For this reason, for the dispersedly encrypted to-be-processed data fragments, the step S420 further includes sending at least part of the to-be-processed data fragments to a multi-party secure computing system in communication with the service processing system, so that the multi-party secure computing system performs the service processing task on each to-be-processed data fragment based on a multi-party secure protocol.

Here, according to a transmission protocol of data fragments of the service processing system and the multi-party secure computing system, the terminal device sends at least part of the data fragments to be processed to the multi-party secure computing system. The service processing system at least comprises terminal equipment and also can comprise server-side equipment according to the logic of the service processing task. According to the multiparty security computing protocol, each computing node in the multiparty computing security system performs multiparty security computing on the received to-be-processed data fragments and obtains dispersedly held computing result fragments. The service processing system can recover the calculation result by selecting a plurality of calculation result fragments, and the calculation result is used for completing the service processing task.

Taking a terminal device as a cash-collecting terminal device, wherein an artificial intelligence model operated by an untrusted execution environment of the terminal device is used for extracting human face feature data in a human face image for description, the cash-collecting terminal device operates a payment service processing task under the operation of a salesman, the cash-collecting terminal device acquires the amount of money input by the salesman and a human face image shot by a camera device connected with the cash-collecting terminal device during the execution of the payment service processing task, operates the artificial intelligence model in the untrusted execution environment of the cash-collecting terminal device to extract the human face feature data in the human face image and dispersedly process the human face feature data into human face feature data fragments, and under the coordination of a server device, the cash-collecting terminal device sends request information to one or more certain computing nodes in a multi-party safety computing system so as to distribute the human face feature data fragments, each computing node establishes safe transmission communication with the cash-registering terminal device based on a cryptography technology and obtains at least partial human face feature data fragments; and each computing node in the multi-party safety computing system executes the identification operation of the face characteristic data according to a preset multi-party safety protocol so as to match the face characteristic data with the fund account, the matched computing result is recovered in the server-side equipment, and the server-side equipment continues to execute the transfer of the collection amount in the matched fund account to the fund account corresponding to the cash-receiving terminal equipment. The step of confirming the credibility verification result can be executed by a multi-party safety computing system, therefore, when the multi-party safety computing system receives request information generated for transmitting the facial feature data fragments, the multi-party safety computing system also constructs safety transmission communication with the cash register terminal device to obtain the credibility verification result, and when the credibility verification result is confirmed to be really credible, the constructed safety transmission communication with the untrusted execution environment of the cash register terminal device is completed, so that the artificial intelligence model used by the payment business processing task and the facial feature data provided by the artificial intelligence model are ensured to be safe. The step of confirming the credibility verification result may also be executed by the server device (or the terminal device), and the multiparty security computing system needs to obtain authorization of the server device (or the terminal device) when receiving the facial feature data fragment, where the authorization may be sent to the multiparty security computing system by the server device (or the terminal device) after confirming the credibility verification result.

It should be noted that the payment transaction processing task is only an example, and in other payment transaction processing tasks, the data to be processed includes: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction. Wherein, the identification result data of the biological characteristics can be identity identification result data and the like; the biometric data may be fingerprint feature data, lip language feature data, or the like.

It should be noted that the related business processing task may also be a business processing task based on identity authentication, or other business processing tasks such as a business processing task based on biometric identification. The service processing task example based on identity authentication includes: the system comprises an access control business processing task, a financial account business processing task, an insurance business processing task and the like. Examples of biometric-based business processing tasks include: an animal and plant identification service processing task, an account authentication service processing task and the like.

In other business process tasks, the artificial intelligence model can further include at least one of: a biometric recognition model, an image recognition model, or a text recognition model. Correspondingly, the data to be processed comprises: recognition result data of the artificial intelligence model, or data extracted by the artificial intelligence model. The identification result data of the artificial intelligence model includes, for example, plant identification result data, expression identification result data, gesture identification result data, semantic identification result data, or the like. Examples of extracted data include: feature data for clustering, local feature data, global feature data, and the like.

In addition, according to the aforementioned descriptions regarding various examples of boot verification, the trusted execution environment sets a use limit related to version or time for the result of the trust verification.

In some examples, the trustworthiness verification result is related to a version of the artificial intelligence model. In other words, the initiation of trustworthiness verification is set in accordance with the version update of the artificial intelligence model. Correspondingly, when the credibility verification result is confirmed, the version information of the artificial intelligence model corresponding to the credibility verification result is also confirmed. For example, the trusted execution environment of the terminal device provides the credibility verification result and the version information of the corresponding artificial intelligence model according to the reading operation of the untrusted execution environment, and the untrusted execution environment compares the version information of the artificial intelligence model stored in the untrusted execution environment with the version information from the trusted execution environment, and determines whether the trusted verification result is trusted. For another example, the server device obtains the trustiness verification result and the version information V1 of the corresponding artificial intelligence model from the trusted execution environment of the terminal device, obtains the version information V1 'of the artificial intelligence model provided by the untrusted execution environment of the terminal device, compares the version information V1 and V1', and determines whether the trustiness verification result is trusted.

It should be noted that, during the service processing task, the manner in which the computer device related to the service processing task performs confirmation by combining the version information and the credibility verification result is merely an example, and a signature may also be generated by using the credibility verification result and the version information, so that the computer device performs confirmation by means of signature verification and the like.

In still other examples, the trust verification result is valid for a term. In other words, the initiation of the trustworthiness verification is set in accordance with the verification period, verification interval, etc. of the artificial intelligence model. Correspondingly, when the credibility verification result is confirmed, the time-related information of the artificial intelligence model corresponding to the credibility verification result is also confirmed. For example, the trusted execution environment of the terminal device provides the information of the trusted verification result and the current verification period according to the reading operation of the untrusted execution environment, and the untrusted execution environment determines whether the current time is in the current verification period according to the system time to determine that the trusted verification result is valid and to determine whether the trusted verification result is trusted. For another example, the server device obtains the trusted verification result and the corresponding verification completion time from the trusted execution environment of the terminal device, determines that a time difference between the current system time and the verification completion time is not greater than the verification interval, and determines whether the trusted verification result is trusted.

In other examples, the trusted execution environment monitors usage limits of stored trustworthiness verification results and deletes or marks failure of trustworthiness verification results when a lifetime is exceeded, for validation operations during execution of the business process task accordingly.

It should be noted that the above examples related to usage limitation can be used alternatively or in combination, and are not described in detail herein.

Taking a service processing system constructed by a terminal device and a server device as an example, an execution process of the service processing system executing a service processing task is described, please refer to fig. 6, which is a flowchart illustrating the service processing system executing the service processing task.

In step S510, the terminal device runs the artificial intelligence model in its untrusted execution environment during the running of the business processing task, so as to obtain data to be processed.

Here, the step S510 is the same as or similar to the step S410, and is not described in detail here.

In step S520, during the operation of the service processing task, in a state that the credibility verification result is confirmed to be authentic, the server device and the terminal device cooperatively process the data to be processed in the terminal device to execute a corresponding service processing task.

Here, the step S520 is the same as or similar to the previous step S420 in which the service end device and the terminal device cooperatively execute the service processing task, and is not described in detail here.

The application also provides a first software trusted verification system, which operates in terminal equipment comprising a trusted execution environment and an untrusted execution environment. The first software credibility verification system verifies the credibility of the artificial intelligence model for the software functions provided by the at least one verification executive program during operation, modules in the first software credibility verification system and the cooperative cooperation among the modules. Wherein the first software trusted verification system comprises: the device comprises a verification starting module and a verification module. In some examples, please refer to fig. 7, which illustrates an architecture diagram of a first software trust verification system, wherein the first software trust verification system further comprises a first interface module 613.

Referring to fig. 7, the first interface module 613 is configured to obtain a verification executive program required for the trust verification; wherein the verification executive is executed in the trusted execution environment to verify the trustworthiness of the artificial intelligence model running in the untrusted execution environment. Here, the first interface module 613 is a software module configured in a trusted execution environment based on a network interface protocol for network transmission with an external device, and corresponds to a communication step of communicating with the trusted authentication server in the aforementioned authentication method, so as to obtain an authentication executive program required for the trustworthiness authentication from the trusted authentication server 2. Here, the first interface module 613 obtains the verification executable in the same or similar way as the verification method described above, and therefore, the details thereof are not described herein. For example, a secure communication is constructed using cryptography techniques to transmit an authentication executive, etc.

Referring to fig. 7, the authentication initiation module 612 is used to initiate an authentication module 611. Here, the manner in which the verification start module 612 starts the verification module 611 may correspond to any one or more of the verification start steps of the aforementioned verification methods. Accordingly, the logic and functions involved in the authentication initiation step are referenced herein. For example, based on the monitored update operation of the artificial intelligence model 710, a plausibility verification of the updated artificial intelligence model is initiated. As another example, a plausibility verification of the invoked artificial intelligence model 710 is initiated based on the monitored invocation of the artificial intelligence model 710. A plausibility verification of the artificial intelligence model 710 is then initiated, e.g., according to a preset verification period.

The verification module is used for verifying the credibility of the artificial intelligence model running in the untrusted execution environment in the trusted execution environment to obtain a verification result; and the credibility verification result is used for credibility verification of computer equipment processing the data output by the artificial intelligence model. The authentication module corresponds to the authentication step in the authentication method when executed, and the logic and functions involved in the authentication step are referred to herein.

According to the verification type of the credibility verification, the verification module comprises a first verification sub-module, a second verification sub-module and a third verification sub-module (none of which is shown).

The first verification sub-module is used for enabling the artificial intelligence model to run in the untrusted execution environment by utilizing first verification input data extracted from the trusted execution environment; and performing operation safety verification on a first operation result generated during the operation of the artificial intelligence model in the trusted execution environment. The first authentication submodule, when executed, corresponds to an operational security authentication step in the authentication method, and the logic and functions involved in the operational security authentication step are hereby incorporated by reference.

The second verification submodule is used for enabling the artificial intelligence model to run in the untrusted execution environment by utilizing at least one piece of second verification input data extracted from the trusted execution environment and outputting each second running result corresponding to each piece of second verification input data; and performing operability verification on each second verification result in the trusted execution environment. The second verification submodule, when executed, corresponds to an operability verification step in the verification method, and the logic and functions involved in the operability verification step are hereby incorporated herein.

And the third verification submodule is used for verifying the integrity of each file required by the operation of the artificial intelligence model based on a cryptographic technique in the trusted execution environment. The third verification submodule, when executed, corresponds to an integrity verification step in a verification method, and the logic and functions involved in the integrity verification step are hereby incorporated by reference.

The credibility verification result obtained by the credibility verification operation of the software credibility verification system is used when the terminal equipment executes the business processing task, so as to confirm that the artificial intelligence model and the operation result thereof are credible. To this end, the software trusted verification system further provides a second interface module (not shown) for providing a transmission function when called for the result of the trusted verification. Here, the second interface module is configured to provide any one of the following transmissions: 1) providing the credibility verification result to a business processing task configured in the terminal equipment, so that the business processing task can perform subsequent processing on the operation result of the artificial intelligence model when the credibility verification result is confirmed to be credible; 2) and sending the credibility verification result to service processing server equipment communicated with the terminal equipment so that the service processing task can perform subsequent processing on the operation result of the artificial intelligence model when confirming that the credibility verification result is reliable.

Here, the second interface module executes the validation step applied in the service processing method, and therefore, the logic and functions related to the trust verification result reading operation, the network transmission operation, and the like, of the validation step are referred to herein.

Referring to fig. 10, the present application further provides a second software trust verification system. Unlike the first software trusted verification system, the second software trusted verification system is configured in the aforementioned verification device 8 and operates in the verification device 8 including the trusted execution environment, and the verification device 8 communicates with the terminal device 7 including the untrusted execution environment in data to verify the authenticity of the artificial intelligence model 710 operating in the untrusted execution environment. The artificial intelligence model 710 is also invoked by the business process tasks 720 to run to provide a running result for the business process tasks.

Here, compared with the aforementioned first software trusted verification system, the execution processes of the verification module 811, the first interface module 813, and the verification start module 812 included in the second software trusted verification system are the same as or similar to the execution processes of the corresponding verification module 611, the first interface module 613, and the verification start module 612 in the first software trusted verification system, respectively, and are not described in detail here. Unlike the first software trusted verification system, in an example, referring to fig. 10, the second interface module 814 in the second software trusted verification system may provide the trusted verification result to the terminal device for the terminal device to perform a confirmation operation by using a data transmission protocol, such as a transmission protocol of a serial interface or a transmission protocol of a network interface. In yet another example, the second interface module (not shown) in the second software trusted verification system further provides the result of the trusted verification to the service processing end device communicating with the terminal device for the service processing end device to perform a confirmation operation by using a data transmission protocol, such as a transmission protocol of a serial interface or a transmission protocol of a network interface. In this way, the business processing task performs subsequent processing on the operation result of the artificial intelligence model when the credibility verification result is confirmed to be credible.

Based on the above technical idea of service processing, the present application further provides a service processing software system configured in a service processing system at least including a terminal device, where the terminal device is configured to provide an untrusted execution environment and a trusted execution environment, and an artificial intelligence model is installed in the untrusted execution environment.

The service processing software system is a software module in the configuration and service processing system, executes service processing functions by calling a service processing program, and at least comprises a service processing module configured in the terminal equipment.

The service processing module is used for operating the artificial intelligence model in the untrusted execution environment during the operation of the service processing task so as to obtain data to be processed; and the data processing system is used for executing the service processing task by using the data to be processed under the condition that the credibility verification result is confirmed to be credible; the credibility verification result is obtained by performing credibility verification on an artificial intelligence model running in the untrusted execution environment, and the credibility verification result is obtained from the credible execution environment.

Here, the execution procedure of the service processing module corresponds to each step executed by the terminal device in the foregoing steps S410 to S420.

In some examples, the terminal device further comprises a confirmation module configured to confirm the authenticity verification result read from the trusted execution environment in the untrusted execution environment during execution of the business processing task by the business processing module to confirm that the executed artificial intelligence model is authentic.

Taking the service processing module to execute the screen unlocking task as an example, when the terminal device is in the screen locking state, the business processing module executes the unlocking task and monitors the biological data provided by the camera device or the fingerprint acquisition device of the terminal equipment, and inputting the biological data into the artificial intelligence model when receiving the biological data to obtain an operation result whether the operation result matches with the preset biological characteristics, the operation result is used as the data to be processed, when the confirmation module executes the subsequent task of unlocking/maintaining the lock screen by using the data to be processed, the result of the authenticity verification stored in the trusted execution environment of the terminal device is also read for confirmation, when the credibility verification result shows that all kinds of credibility verification of the artificial intelligence model are credible, the service processing module continues to execute unlocking operation according to the feedback of the confirmation module, namely, a display interface of the terminal equipment is switched from a screen locking interface to an unlocking interface (such as a desktop interface and the like); otherwise, the screen locking interface is maintained or a warning prompt is given.

The above examples provide a way for the service processing module in the terminal device to execute the service processing task, but are only by way of example and not limiting on the service processing tasks that can be executed by the service processing module.

In other examples, the confirmation module sends the credibility verification result to a server device in the service processing system, so that the server device confirms the credibility verification result. Still taking the above unlocking task as an example, the service task module instructs the confirmation module to send the credibility verification result in the trusted execution environment to the server device at any time when the unlocking task is not completed, and obtains the confirmation information fed back by the server device, if the confirmation information is trusted, the unlocking task is continuously executed in the trusted state, otherwise, the screen locking state is maintained.

In another embodiment, the service processing system further includes a server device. For convenience of subsequent description, the service operation module configured in the terminal device is referred to as a first service operation module, and the service operation module configured in the server device is referred to as a second service operation module. The confirmation module configured in the terminal device is referred to as a first confirmation module, and the confirmation module configured in the server device is referred to as a second confirmation module.

The first service operation module and the second service operation module may correspond to service processing tasks cooperatively executed by the terminal device and the server device in steps S410-S420.

Taking the example that the first service operation module and the second service operation module cooperatively execute the payment task, the first service operation module executes the payment task of transferring the payment amount c in the fund account P of the user to the fund account Q under the payment operation of the user, the first service operation module receives the biological data provided by the camera device or the fingerprint acquisition device of the terminal device during the execution, inputs the biological data into the artificial intelligence model to obtain the extracted biological characteristic information, sends the biological characteristic information to the second service operation module, the second service operation module performs characteristic matching and determines the fund account P corresponding to the biological characteristic information, and executes the subsequent payment task of transferring the payment amount c in the fund account P to the fund account Q. In some examples, before the second service running module performs the feature matching or before the second service running module performs operations such as transfer, the second confirmation module obtains and confirms a credibility verification result in a trusted execution environment in the terminal device, and when the credibility verification result indicates that all kinds of credibility verifications of the artificial intelligence model are trusted, the second service running module performs subsequent feature matching operations or performs transfer operations based on the confirmation information provided by the second confirmation module; otherwise, the second service operation module gives a transfer failure prompt or a matching failure prompt and the like. In other examples, before the first business processing module starts the artificial intelligence model or sends out the data to be processed, the confirmation module reads and confirms the credibility verification result in the trusted execution environment, and when the credibility verification result indicates that all kinds of credibility verifications of the artificial intelligence model are trusted, the second business operation module starts the artificial intelligence model or sends out the data to be processed based on the confirmation information provided by the second confirmation module, and sends the data to be processed to the second business operation module for the second business operation module to continue to execute subsequent operations.

The first service processing module and the second service processing module may also execute a service processing task for the encrypted to-be-processed data, which corresponds to the process of processing the encrypted to-be-processed data in the foregoing step S420, and will not be described in detail herein.

Taking a terminal device as a cash-receiving terminal device, wherein an artificial intelligence model operated in an untrusted execution environment of the terminal device is used for extracting face feature data in a face image for description, a first service processing module is operated under the operation of a salesman to execute a payment service processing task, the first service processing module acquires the amount of money input by the salesman and a face image shot by a camera device connected with the cash-receiving terminal device during the execution of the payment service processing task, the artificial intelligence model is operated in the untrusted execution environment of the cash-receiving terminal device to extract the face feature data in the face image, the first service processing module disperses and processes the face feature data into face feature data fragments, a second service processing module coordinates with communicable computing nodes to form a multi-party security computing system, and instructs the first service processing module to send request information to one or more computing nodes in the multi-party security computing system so as to distribute the face feature data The method comprises the steps that feature data are segmented, each computing node establishes safe transmission communication with a cash register terminal device based on a cryptography technology, and at least part of face feature data are segmented; and each computing node in the multi-party safety computing system executes the identification operation of the face characteristic data according to a preset multi-party safety protocol so as to match the face characteristic data with the fund account, the matched computing result is recovered in the second business processing module, and the second business processing module continues to execute the step of transferring the collection amount in the matched fund account to the fund account corresponding to the cash-receiving terminal equipment. The step of confirming the credibility verification result can be executed by a multi-party safety computing system, therefore, when the multi-party safety computing system receives request information generated for transmitting the facial feature data fragments, the multi-party safety computing system also constructs safety transmission communication with the cash register terminal device to obtain the credibility verification result, and when the credibility verification result is confirmed to be really credible, the constructed safety transmission communication with the untrusted execution environment of the cash register terminal device is completed, so that the artificial intelligence model used by the payment business processing task and the facial feature data provided by the artificial intelligence model are ensured to be safe. The step of confirming the credibility verification result may also be executed by a second confirmation module (or a first confirmation module), and the multiparty security computing system needs to obtain authorization of the second confirmation module (or the first confirmation module) when receiving the facial feature data fragment, where the authorization may be sent to the multiparty security computing system by the second confirmation module (or the first confirmation module) after confirming the credibility verification result.

Please refer to fig. 8, which is a schematic diagram illustrating a network architecture provided based on the authentication scheme and the service processing scheme described in the present application. Taking the example shown in fig. 8, the terminal device is configured with an untrusted execution environment and a trusted execution environment using hardware devices and software programs installed in advance. The hardware devices include a storage device, a processing device, an acquisition device, and the like, and the software programs include a verification execution program, a service processing program, a program describing an artificial intelligence model, and the like. Calling a corresponding program in an untrusted execution environment to run an artificial intelligence model, a business processing module and the like and store various data such as biological data, a running result and the like during the running of the artificial intelligence model and the business processing module; and calling a corresponding program in the trusted execution environment to run a verification module and the like and storing a credibility verification result obtained by the verification module. The server side equipment comprises a credible verification server side, a multi-party safety computing system and business service equipment. The credibility verification server side is computer equipment which is matched with the terminal equipment to carry out credibility verification; the Multi-Party Secure computing system executes part of data processing in the business processing task by using a Multi-Party Secure computing protocol (MPC for short); the service device is a computer device which executes service processing tasks in cooperation with the terminal device. The business service equipment is in communication connection with the credibility verification server and the multi-party security computing system. The trusted verification server downloads the verification execution program to a trusted execution environment of the terminal device through a secure communication channel in advance.

The service processing module executes a service processing task in the running period, biological data are obtained through the acquisition device according to the service processing task, the biological data are input into the running artificial intelligence model, the artificial intelligence model is detected by the verification starting module and starts the verification module in the running period, the verification module conducts credibility verification on the artificial intelligence model by utilizing the biological data, the obtained credibility verification result is stored in a credible execution environment, the running result obtained by running the artificial intelligence model is encrypted to obtain data fragments to be processed, and the terminal equipment requests the service equipment to conduct follow-up processing on the data fragments to be processed so as to continue to execute the service processing task. The business service equipment acquires a credibility verification result to confirm the credibility of an artificial intelligence model and the to-be-processed data fragment in the terminal equipment on one hand, selects a plurality of computing nodes to form a multi-party security computing system on the other hand, instructs the terminal equipment to send at least part of the to-be-processed data fragment to the multi-party security computing system after the credibility is confirmed so as to execute multi-party security computing to obtain computing results respectively held by the computing nodes, and appoints external service equipment to carry out recovery operation by using the computing results by the business service equipment or the business service equipment to obtain processing data of a business processing part executed by the multi-party security computing system and complete a business processing task based on the processing data.

It should be noted that the above examples are only examples, and the above examples are partially replaced according to the above mentioned examples, and the obtained new examples are still under the technical architecture of the present solution.

The present application also provides a computer readable and writable storage medium storing a computer program of a data processing method, which when executed implements the service processing method described in the above embodiment.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application.

In the embodiments provided herein, the computer-readable and writable storage medium may include read-only memory, random-access memory, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, a USB flash drive, a removable hard disk, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. It should be understood, however, that computer-readable-writable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but are intended to be non-transitory, tangible storage media. Disk and disc, as used in this application, includes Compact Disc (CD), laser disc, optical disc, Digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.

In one or more exemplary aspects, the functions described in the computer program of the data processing method described herein may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. The steps of a method or algorithm disclosed herein may be embodied in a processor-executable software module, which may be located on a tangible, non-transitory computer-readable and/or writable storage medium. Tangible, non-transitory computer readable and writable storage media may be any available media that can be accessed by a computer.

The flowcharts and block diagrams in the figures described above of the present application illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Based on the technical frameworks reflected by the examples described by the service processing method, the service processing system based on the artificial intelligence model, the terminal device, the server device, the service processing software system and the computer readable storage medium, the application discloses the following technical scheme:

1. a business processing method is suitable for a business processing system at least comprising a terminal device, wherein an artificial intelligence model operating in an untrusted execution environment is configured in the terminal device, and the business processing method comprises the following steps:

the artificial intelligence model is operated during the operation of the service processing task of the terminal equipment to obtain data to be processed;

under the condition that the credibility verification result of the artificial intelligence model is confirmed to be credible, the data to be processed is utilized to execute the business processing task; the trust verification result is from a trusted execution environment.

2. The traffic processing method according to embodiment 1, wherein the means for confirming the result of the plausibility check includes:

during execution of the business processing task, validating the trustworthiness verification results read from the trusted execution environment in the untrusted execution environment to validate that the executed artificial intelligence model is trustworthy; or

And sending the credibility verification result to server equipment in the service processing system so that the server equipment can confirm the credibility verification result.

3. The service processing method according to embodiment 2, wherein the step of sending the credibility verification result to the server device includes: and sending the credibility verification result to the server side equipment by utilizing the safe data communication between the credible execution environment and the server side equipment.

4. The business process method of embodiment 1, wherein said credibility verification result is associated with a version of said artificial intelligence model; or the credibility verification result is valid for a term.

5. The service processing method according to embodiment 1, further comprising a step of encrypting the data to be processed.

6. The service processing method according to embodiment 5, wherein the encryption processing mode includes: dispersing the data to be processed into N data fragments to be processed; wherein N is more than 1.

7. The business processing method according to embodiment 6, wherein the step of executing the business processing task by using the data to be processed includes:

and sending at least part of the data fragments to be processed to a multi-party security computing system which is communicated with the service processing system, so that the multi-party security computing system can execute the service processing task on each data fragment to be processed based on a multi-party security protocol.

8. The transaction processing method of embodiment 7 wherein the computing nodes in the multi-party secure computing system comprise: computer equipment in the business processing system.

9. The service processing method according to embodiment 5, wherein the encryption processing mode includes: and encrypting the data to be processed by using the key.

10. The business processing method according to embodiment 9, wherein the step of executing the business processing task by using the data to be processed includes: and sending the encrypted data to be processed to server equipment in the service processing system so that the server equipment executes data processing operation in the service processing task by using the encrypted data to be processed.

11. The business process method of embodiment 1, wherein the artificial intelligence model comprises at least one of: a biometric recognition model, an image recognition model, or a text recognition model.

12. The service processing method according to embodiment 11, wherein the data to be processed includes: recognition result data of the artificial intelligence model, or data extracted by the artificial intelligence model.

13. The traffic processing method according to embodiment 12, wherein the data to be processed includes: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction.

14. The service processing method according to embodiment 1 or 12, wherein the service processing task includes: the business processing task based on identity authentication or the business processing task based on biological characteristic identification.

15. The business processing method according to embodiment 1, wherein the step of executing the business processing task by using the data to be processed includes: and executing data processing operation in the business processing task on the data to be processed in the untrusted execution environment.

16. The business process method of embodiment 1, wherein said running said artificial intelligence model in an untrusted execution environment; the business processing method further comprises the following steps executed in the trusted execution environment: and reading credibility verification information provided by the artificial intelligence model from the untrusted execution environment, and performing credibility verification on the artificial intelligence model according to the credibility verification information to obtain a credibility verification result.

17. The business process method of embodiment 1, wherein said step of running said artificial intelligence model in an untrusted execution environment comprises: and operating the artificial intelligence model to perform data processing related to biological characteristic processing on the acquired data provided by the acquisition device of the terminal equipment.

18. The business processing method of embodiment 1, wherein the trusted execution environment is configured in the terminal device; or the trusted execution environment is configured in the verification device, wherein the terminal device is in communication connection with the verification device.

19. A business processing method is suitable for a business processing system which is constructed by terminal equipment and server-side equipment, and comprises the following steps:

obtaining a credibility verification result from a credible execution environment; the credibility verification result is obtained by verifying the credibility of the artificial intelligence model operated in the untrusted execution environment in the terminal equipment;

during the operation of the business processing task, under the condition that the credibility verification result is confirmed to be credible, cooperatively processing the data to be processed in the terminal equipment with the terminal equipment so as to execute the corresponding business processing task; wherein the data to be processed is obtained by running the artificial intelligence model in the untrusted execution environment.

20. The traffic processing method according to embodiment 19, wherein the result of the trustworthiness verification is from a trusted execution environment of the terminal device or from a verification device in communication with the terminal device.

21. The business process method of embodiment 19 wherein said trustworthiness verification result is associated with a version of said artificial intelligence model; or the result of the plausibility verification is valid.

22. The transaction processing method according to embodiment 19 or 20, wherein the step of obtaining the result of the trust verification from a trusted execution environment comprises:

obtaining the credibility verification result by utilizing the safe data communication between the credible execution environment and the server side equipment;

and confirming the credibility of the acquired data to be processed by confirming the credibility verification result.

23. The traffic processing method according to embodiment 19, wherein the step of processing the data to be processed in the terminal device in cooperation with the terminal device to execute the corresponding traffic processing task comprises: data processing operations are performed on the received encrypted data to be processed.

24. The traffic processing method according to embodiment 19, wherein the step of processing the data to be processed in the terminal device in cooperation with the terminal device to execute the corresponding traffic processing task comprises:

and distributing at least one piece of data to be processed from the terminal equipment to a multi-party security computing system communicated with the business processing system, so that the multi-party security computing system can execute the business processing task on each piece of data to be processed based on a multi-party security protocol.

25. The transaction processing method according to embodiment 24, wherein the computing nodes in the multi-party secure computing system comprise: and the terminal equipment or the server equipment in the service processing system.

26. The business process method of embodiment 19 wherein the artificial intelligence model comprises: a biometric identification model, an image identification model, or a text identification model.

27. The traffic processing method according to embodiment 26, wherein the data to be processed includes: recognition result data of the artificial intelligence model, or data extracted by the artificial intelligence model.

28. The traffic processing method according to embodiment 27, wherein the data to be processed includes: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction.

29. The business process method of embodiment 19 or 28, wherein the business process task comprises: a business processing task based on identity authentication, or a business processing task based on biometric identification.

30. An artificial intelligence model-based business processing system, comprising:

a terminal device, at least providing an untrusted execution environment, configured to execute the service processing method according to any one of embodiments 1 to 18;

and the server side equipment is communicated with the terminal equipment and is used for sending at least one pre-generated verification execution program to the terminal equipment so as to obtain a credibility verification result after the execution of a credible execution environment in the terminal equipment.

31. The service processing system based on the artificial intelligence model according to embodiment 30, wherein the server device executes the service processing method according to any one of embodiments 19 to 29 based on a trigger operation of the terminal device.

32. A terminal device, comprising:

the storage device is used for storing a program for describing the artificial intelligence model, at least one business processing program and a credibility verification result;

a processing device in communication with the memory device over a bus, comprising:

a first processing unit, configured in an untrusted execution environment, for invoking and executing the at least one business processing program, and running the artificial intelligence model in the untrusted execution environment, to execute the business processing method according to any one of embodiments 1 to 18;

the second processing unit is configured in a trusted execution environment and used for reading the credibility verification result;

wherein data is communicated between the trusted execution environment and the untrusted execution environment.

33. The terminal device of embodiment 32, wherein the terminal device further comprises a collection means for collecting biological data; the artificial intelligence model is used for carrying out feature extraction or identification processing on the acquired biological data.

34. The terminal device of embodiment 32, wherein the terminal device comprises: payment terminal equipment, mobile terminal equipment, entrance guard terminal equipment or security protection monitoring terminal equipment.

35. A terminal device, comprising:

processing means, in communication with the storage means via a bus, configured in an untrusted execution environment, for invoking and executing the at least one business process, and running the artificial intelligence model in the untrusted execution environment, to execute the business process method according to any one of embodiments 1 to 18;

the interface device is used for being in communication connection with a verification device to obtain a credibility verification result; wherein the verification device provides a trusted execution environment and stores the trustworthiness verification result.

36. A server device, comprising:

the interface device is used for receiving data to be processed and a credibility verification result from the terminal equipment;

storage means for storing at least one program;

processing means for invoking said at least one program to coordinate said interface means and storage means to perform a business process method as described in any of embodiments 19-29.

37. The server-side device of embodiment 36, wherein the interface means is further configured to receive an artificial intelligence model to be verified;

the storage device also stores at least one verification executive program corresponding to the artificial intelligence model;

the processing means is further for coordinating the interface means and the storage means to perform the steps of: sending the at least one verification executive to the terminal equipment provided with the artificial intelligence model;

wherein the at least one verification executive is used for performing credibility verification on the artificial intelligence model running in the untrusted execution environment of the terminal equipment.

38. A business process software system configured in a business process system including at least a terminal device having an artificial intelligence model configured therein to operate in an untrusted execution environment, the business process software system comprising:

the service operation module is used for operating the artificial intelligence model during the operation of the service processing task so as to obtain data to be processed; and the data processing system is used for executing the service processing task by using the data to be processed under the condition that the credibility verification result is confirmed to be credible; the credibility verification result is obtained by performing credibility verification on an artificial intelligence model running in the untrusted execution environment, and the credibility verification result is from a credible execution environment.

39. The business process software system of embodiment 38 further comprising a validation module for validating said trustworthiness verification result by:

validating, in the untrusted execution environment, the trustworthiness verification read from the trusted execution environment during execution of the business processing task by the business processing module to validate that the executed artificial intelligence model is trustworthy; or

40. The business process software system of embodiment 39, wherein the validation module is configured to send the trustworthiness verification result to the server device using secure data communication between the trusted execution environment and the server device.

41. The business process software system of embodiment 38 wherein said trustworthiness verification result is associated with a version of said artificial intelligence model; or the credibility verification result is valid for a term.

42. The business process software system of embodiment 38, wherein the business execution module is further configured to encrypt the data to be processed.

43. The business process software system of embodiment 42 wherein the encryption process comprises: dispersing the data to be processed into N data fragments to be processed; wherein N is more than 1.

44. The service processing software system of embodiment 43, wherein the service running module is configured to send at least part of the to-be-processed data fragments to a multi-party secure computing system in communication with the service processing system, so that the multi-party secure computing system executes the service processing task on each to-be-processed data fragment based on a multi-party secure protocol.

45. The business process software system of embodiment 42 wherein the encryption process comprises: and encrypting the data to be processed by using the key.

46. The business processing software system of embodiment 45, wherein the running module is configured to send the encrypted to-be-processed data to the server device, so that the server device executes the data processing operation in the business processing task by using the encrypted to-be-processed data.

47. The business process software system of embodiment 38 wherein the artificial intelligence model comprises at least one of: a biometric recognition model, an image recognition model, or a text recognition model.

48. The business process software system of embodiment 47 wherein the data to be processed comprises: recognition result data of the artificial intelligence model, or data extracted by the artificial intelligence model.

49. The business process software system of embodiment 48 wherein the data to be processed comprises: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction.

50. The business process software system of embodiment 38 or 48, wherein the business process tasks comprise: the business processing task based on identity authentication or the business processing task based on biological characteristic identification.

51. The business process software system of embodiment 38, wherein the business execution module is configured to perform data processing operations in the business process task on the data to be processed in the untrusted execution environment.

52. The business process software system of embodiment 38, further comprising a verification module configured to read credibility verification information provided by the artificial intelligence model from the untrusted execution environment, and perform credibility verification on the artificial intelligence model according to the credibility verification information to obtain a credibility verification result.

53. The business process software system of embodiment 38 wherein the manner in which the business execution module executes the artificial intelligence model in an untrusted execution environment comprises: and operating the artificial intelligence model to perform data processing related to biological characteristic processing on the acquired data provided by the acquisition device of the terminal equipment.

54. The business process software system of embodiment 38 wherein said trusted execution environment is configured in said terminal device; or the trusted execution environment is configured in the verification device, wherein the terminal device is in communication connection with the verification device.

55. A service processing software system configured in a service processing system constructed by a terminal device and a server device, wherein the service processing software system comprises:

the service operation module is used for acquiring a credibility verification result from the terminal equipment; the credibility verification result is obtained by verifying the credibility of the artificial intelligence model operated in the untrusted execution environment in the terminal equipment; and the data processing system is used for processing the data to be processed in the terminal equipment in a coordinated manner with the terminal equipment to execute the corresponding business processing task in a state that the credibility verification result is confirmed to be credible during the running of the business processing task; wherein the data to be processed is obtained by running the artificial intelligence model in the untrusted execution environment.

56. The business process software system of embodiment 55, wherein said authenticity verification result is pre-stored in a trusted execution environment of said terminal device.

57. The business process software system of embodiment 55 wherein said trustworthiness verification result is associated with a version of said artificial intelligence model; or the credibility verification result is valid for a term.

58. The business process software system of embodiment 55 or 56, wherein the business execution module is configured to perform the following processes:

obtaining the credibility verification result by using the safety data communication between the terminal equipment and the server-side equipment;

59. The service processing software system of embodiment 55, wherein the service running module is configured to receive encrypted data to be processed, so as to process the encrypted data to be processed in cooperation with the terminal device.

60. The business processing software system of embodiment 55, wherein the business operation module is configured to allocate at least one piece of data to be processed from the terminal device to a multi-party secure computing system in communication with the business processing system, so that the multi-party secure computing system performs the business processing task on each piece of data to be processed based on a multi-party secure protocol.

61. The business process software system of embodiment 55 wherein said artificial intelligence model comprises: a biometric identification model, an image identification model, or a text identification model.

62. The business process software system of embodiment 61 wherein the data to be processed comprises: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction.

63. The business process software system of embodiment 55 wherein the data to be processed comprises: identification result data of the biological characteristics obtained through identification, or biological characteristic data obtained through extraction.

64. The business process software system of embodiment 55 or 61, wherein the business process tasks comprise: a business processing task based on identity authentication, or a business processing task based on biometric identification.

65. A computer-readable storage medium in which at least one program is stored, which when invoked executes and implements a business process method as in any one of embodiments 1-18, or executes and implements a business process method as in any one of embodiments 19-29.

The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.

Claims

1. A service processing method is applied to a service processing system at least comprising a terminal device, wherein an artificial intelligence model operating in an untrusted execution environment is configured in the terminal device, and the service processing method comprises the following steps:

2. A service processing method is applicable to a service processing system constructed by a terminal device and a server device, and comprises the following steps:

3. A business processing system based on an artificial intelligence model, comprising:

a terminal device providing at least an untrusted execution environment for executing the service processing method according to claim 1;

4. The artificial intelligence model-based business processing system of claim 3, wherein the server device executes the business processing method of claim 2 based on a trigger operation of the terminal device.

5. A terminal device, comprising:

a first processing unit, configured in an untrusted execution environment, for invoking and executing said at least one business process, and running said artificial intelligence model in said untrusted execution environment, for executing the business process method of claim 1;

6. A terminal device, comprising:

processing means, in communication with said storage means via a bus, configured in an untrusted execution environment, for invoking and executing said at least one business process, and running said artificial intelligence model in said untrusted execution environment, for performing the business process method of claim 1;

7. A server-side device, comprising:

storage means for storing at least one program;

processing means for invoking said at least one program to coordinate said interface means and storage means to perform the business process method of claim 2.

8. A business process software system configured in a business process system including at least a terminal device, the terminal device configured with an artificial intelligence model operating in an untrusted execution environment, the business process software system comprising:

9. A service processing software system configured in a service processing system constructed by a terminal device and a server device, wherein the service processing software system includes:

10. A computer-readable storage medium characterized by storing at least one program which, when called, executes and implements the service processing method according to claim 1, or executes and implements the service processing method according to claim 2.